Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 608 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1585. Min Range: -3.1585
Max Act: 3.1585. Min Act: -0.1700
Data Index: 719652 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1585. Min Range: -3.1585
Max Act: 3.0640. Min Act: -0.1700
Data Index: 3053271 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1585. Min Range: -3.1585
Max Act: 3.1113. Min Act: -0.1700
Data Index: 4281423 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1585. Min Range: -3.1585
Max Act: 3.0797. Min Act: -0.1700
Data Index: 5131284 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1585. Min Range: -3.1585
Max Act: 3.0640. Min Act: -0.1700
Data Index: 2116164 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1585. Min Range: -3.1585
Max Act: 3.0482. Min Act: -0.1700
Data Index: 7738293 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1585. Min Range: -3.1585
Max Act: 3.0482. Min Act: -0.1700
Data Index: 5286725 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1585. Min Range: -3.1585
Max Act: 3.0166. Min Act: -0.1700
Data Index: 5643807 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1585. Min Range: -3.1585
Max Act: 3.0324. Min Act: -0.1700
Data Index: 1269687 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1585. Min Range: -3.1585
Max Act: 3.0166. Min Act: -0.1700
Data Index: 697986 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1585. Min Range: -3.1585
Max Act: 2.9850. Min Act: -0.1700
Data Index: 2116162 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1585. Min Range: -3.1585
Max Act: 2.9850. Min Act: -0.1700
Data Index: 7199686 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1585. Min Range: -3.1585
Max Act: 2.9850. Min Act: -0.1700
Data Index: 2611275 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1585. Min Range: -3.1585
Max Act: 2.9692. Min Act: -0.1700
Data Index: 1220041 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1585. Min Range: -3.1585
Max Act: 2.9692. Min Act: -0.1700
Data Index: 6798620 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1585. Min Range: -3.1585
Max Act: 2.9534. Min Act: -0.1700
Data Index: 4007270 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1585. Min Range: -3.1585
Max Act: 2.9534. Min Act: -0.1700
Data Index: 625687 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1585. Min Range: -3.1585
Max Act: 2.9375. Min Act: -0.1700
Data Index: 3677964 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1585. Min Range: -3.1585
Max Act: 2.9217. Min Act: -0.1700
Data Index: 7602861 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1585. Min Range: -3.1585
Max Act: 2.9375. Min Act: -0.1700
Data Index: 3455594 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19