Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2565 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2938. Min Range: -8.2938
Max Act: 8.2938. Min Act: -0.1700
Data Index: 3640695 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2938. Min Range: -8.2938
Max Act: 8.1063. Min Act: -0.1700
Data Index: 7993741 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2938. Min Range: -8.2938
Max Act: 8.0438. Min Act: -0.1700
Data Index: 3963223 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2938. Min Range: -8.2938
Max Act: 8.0438. Min Act: -0.1700
Data Index: 2346573 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2938. Min Range: -8.2938
Max Act: 7.9813. Min Act: -0.1700
Data Index: 6188125 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2938. Min Range: -8.2938
Max Act: 7.9188. Min Act: -0.1700
Data Index: 3259093 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2938. Min Range: -8.2938
Max Act: 7.9188. Min Act: -0.1700
Data Index: 1606366 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2938. Min Range: -8.2938
Max Act: 7.9188. Min Act: -0.1700
Data Index: 6389698 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2938. Min Range: -8.2938
Max Act: 7.9188. Min Act: -0.1700
Data Index: 8701476 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2938. Min Range: -8.2938
Max Act: 7.8563. Min Act: -0.1700
Data Index: 3942852 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2938. Min Range: -8.2938
Max Act: 7.8563. Min Act: -0.1700
Data Index: 5117642 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2938. Min Range: -8.2938
Max Act: 7.8251. Min Act: -0.1700
Data Index: 1913111 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2938. Min Range: -8.2938
Max Act: 7.7938. Min Act: -0.1700
Data Index: 1074000 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2938. Min Range: -8.2938
Max Act: 7.7938. Min Act: -0.1700
Data Index: 5413213 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2938. Min Range: -8.2938
Max Act: 7.7938. Min Act: -0.1700
Data Index: 3594106 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2938. Min Range: -8.2938
Max Act: 7.7626. Min Act: -0.1700
Data Index: 7267537 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2938. Min Range: -8.2938
Max Act: 7.7001. Min Act: -0.1700
Data Index: 4861336 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2938. Min Range: -8.2938
Max Act: 7.7313. Min Act: -0.1700
Data Index: 3896789 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2938. Min Range: -8.2938
Max Act: 7.7001. Min Act: -0.1700
Data Index: 1301133 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2938. Min Range: -8.2938
Max Act: 7.7001. Min Act: -0.1700
Data Index: 5523132 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19