Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2692 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 14.0653. Min Range: -14.0653
Max Act: 14.0653. Min Act: -0.1700
Data Index: 1160189 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.0653. Min Range: -14.0653
Max Act: 8.1278. Min Act: -0.1700
Data Index: 344231 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.0653. Min Range: -14.0653
Max Act: 13.6278. Min Act: -0.1700
Data Index: 362193 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.0653. Min Range: -14.0653
Max Act: 13.7528. Min Act: -0.1700
Data Index: 444389 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.0653. Min Range: -14.0653
Max Act: 13.8778. Min Act: -0.1700
Data Index: 5350386 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.0653. Min Range: -14.0653
Max Act: 11.1903. Min Act: -0.1700
Data Index: 1583747 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.0653. Min Range: -14.0653
Max Act: 12.5653. Min Act: -0.1700
Data Index: 8250845 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.0653. Min Range: -14.0653
Max Act: 9.6903. Min Act: -0.1700
Data Index: 1146364 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.0653. Min Range: -14.0653
Max Act: 12.6278. Min Act: -0.1700
Data Index: 5193363 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.0653. Min Range: -14.0653
Max Act: 12.8153. Min Act: -0.1700
Data Index: 8787267 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.0653. Min Range: -14.0653
Max Act: 13.5653. Min Act: -0.1700
Data Index: 1432436 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.0653. Min Range: -14.0653
Max Act: 9.4403. Min Act: -0.1700
Data Index: 2157614 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.0653. Min Range: -14.0653
Max Act: 13.5028. Min Act: -0.1700
Data Index: 5953943 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.0653. Min Range: -14.0653
Max Act: 12.7528. Min Act: -0.1700
Data Index: 7618717 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.0653. Min Range: -14.0653
Max Act: 13.8153. Min Act: -0.1700
Data Index: 8178231 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.0653. Min Range: -14.0653
Max Act: 12.3153. Min Act: -0.1700
Data Index: 8201045 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.0653. Min Range: -14.0653
Max Act: 11.1903. Min Act: -0.1700
Data Index: 7376333 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.0653. Min Range: -14.0653
Max Act: 12.1903. Min Act: -0.1700
Data Index: 1658059 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.0653. Min Range: -14.0653
Max Act: 12.6278. Min Act: -0.1700
Data Index: 2871305 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.0653. Min Range: -14.0653
Max Act: 13.3153. Min Act: -0.1700
Data Index: 2579469 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19