Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2254 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0020. Min Range: -3.0020
Max Act: 2.9862. Min Act: -0.1700
Data Index: 2069071 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0020. Min Range: -3.0020
Max Act: 2.9704. Min Act: -0.1700
Data Index: 5304432 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0020. Min Range: -3.0020
Max Act: 3.0020. Min Act: -0.1700
Data Index: 3890248 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0020. Min Range: -3.0020
Max Act: 2.9862. Min Act: -0.1700
Data Index: 7782954 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0020. Min Range: -3.0020
Max Act: 2.9546. Min Act: -0.1700
Data Index: 4146932 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0020. Min Range: -3.0020
Max Act: 2.9387. Min Act: -0.1700
Data Index: 6867479 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0020. Min Range: -3.0020
Max Act: 2.9387. Min Act: -0.1700
Data Index: 6170067 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0020. Min Range: -3.0020
Max Act: 2.9387. Min Act: -0.1700
Data Index: 6524839 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0020. Min Range: -3.0020
Max Act: 2.9229. Min Act: -0.1700
Data Index: 4611472 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0020. Min Range: -3.0020
Max Act: 2.9229. Min Act: -0.1700
Data Index: 8340213 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0020. Min Range: -3.0020
Max Act: 2.8912. Min Act: -0.1700
Data Index: 134414 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0020. Min Range: -3.0020
Max Act: 2.8912. Min Act: -0.1700
Data Index: 7106858 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0020. Min Range: -3.0020
Max Act: 2.9071. Min Act: -0.1700
Data Index: 8553197 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0020. Min Range: -3.0020
Max Act: 2.8912. Min Act: -0.1700
Data Index: 7534065 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0020. Min Range: -3.0020
Max Act: 2.8595. Min Act: -0.1700
Data Index: 3792843 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0020. Min Range: -3.0020
Max Act: 2.8753. Min Act: -0.1700
Data Index: 1640325 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0020. Min Range: -3.0020
Max Act: 2.8753. Min Act: -0.1700
Data Index: 2747446 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0020. Min Range: -3.0020
Max Act: 2.8753. Min Act: -0.1700
Data Index: 2083287 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0020. Min Range: -3.0020
Max Act: 2.8753. Min Act: -0.1700
Data Index: 6673742 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0020. Min Range: -3.0020
Max Act: 2.8595. Min Act: -0.1700
Data Index: 1947624 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19