Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 695 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.6197. Min Act: -0.1700
Data Index: 1867882 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.6197. Min Act: -0.1700
Data Index: 5151209 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.5884. Min Act: -0.1700
Data Index: 4565564 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.5572. Min Act: -0.1700
Data Index: 1365595 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.5572. Min Act: -0.1700
Data Index: 5506202 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.5572. Min Act: -0.1700
Data Index: 6115222 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.5572. Min Act: -0.1700
Data Index: 6462950 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.5259. Min Act: -0.1700
Data Index: 5304089 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4947. Min Act: -0.1700
Data Index: 7509151 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4947. Min Act: -0.1700
Data Index: 6382045 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4634. Min Act: -0.1700
Data Index: 3762270 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4634. Min Act: -0.1700
Data Index: 3857476 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4634. Min Act: -0.1700
Data Index: 1016338 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4322. Min Act: -0.1700
Data Index: 3242945 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4634. Min Act: -0.1700
Data Index: 1138720 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4322. Min Act: -0.1700
Data Index: 4832580 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4322. Min Act: -0.1700
Data Index: 3818260 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4009. Min Act: -0.1700
Data Index: 8768435 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4322. Min Act: -0.1700
Data Index: 3004018 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4009. Min Act: -0.1700
Data Index: 1318654 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19