Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1045 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.7598. Min Act: -0.1700
Data Index: 4290282 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.6661. Min Act: -0.1700
Data Index: 8422099 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.4161. Min Act: -0.1700
Data Index: 1485774 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.3848. Min Act: -0.1700
Data Index: 7492233 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.3223. Min Act: -0.1700
Data Index: 2668386 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.3536. Min Act: -0.1700
Data Index: 8067990 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.3223. Min Act: -0.1700
Data Index: 5695567 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.3536. Min Act: -0.1700
Data Index: 5251388 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.2598. Min Act: -0.1700
Data Index: 847175 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.2911. Min Act: -0.1700
Data Index: 1503326 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.2911. Min Act: -0.1700
Data Index: 1588756 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.2911. Min Act: -0.1700
Data Index: 2380786 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.2598. Min Act: -0.1700
Data Index: 7646061 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.2285. Min Act: -0.1700
Data Index: 6377863 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.2598. Min Act: -0.1700
Data Index: 3880891 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.2598. Min Act: -0.1700
Data Index: 2912115 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.2598. Min Act: -0.1700
Data Index: 5971858 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.2911. Min Act: -0.1700
Data Index: 5600245 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.2285. Min Act: -0.1700
Data Index: 1806209 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.2598. Min Act: -0.1700
Data Index: 5518185 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19