Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1223 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4871. Min Range: -5.4871
Max Act: 5.4871. Min Act: -0.1700
Data Index: 791824 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4871. Min Range: -5.4871
Max Act: 5.2996. Min Act: -0.1700
Data Index: 2036023 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4871. Min Range: -5.4871
Max Act: 5.1121. Min Act: -0.1700
Data Index: 2450055 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4871. Min Range: -5.4871
Max Act: 5.1433. Min Act: -0.1700
Data Index: 6410882 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4871. Min Range: -5.4871
Max Act: 5.0808. Min Act: -0.1700
Data Index: 1113473 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4871. Min Range: -5.4871
Max Act: 5.1121. Min Act: -0.1700
Data Index: 7075090 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4871. Min Range: -5.4871
Max Act: 5.0496. Min Act: -0.1700
Data Index: 2450056 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4871. Min Range: -5.4871
Max Act: 5.0183. Min Act: -0.1700
Data Index: 2450060 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4871. Min Range: -5.4871
Max Act: 4.9871. Min Act: -0.1700
Data Index: 6354151 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4871. Min Range: -5.4871
Max Act: 5.0183. Min Act: -0.1700
Data Index: 2745195 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4871. Min Range: -5.4871
Max Act: 4.9871. Min Act: -0.1700
Data Index: 7121456 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4871. Min Range: -5.4871
Max Act: 4.9871. Min Act: -0.1700
Data Index: 6476971 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4871. Min Range: -5.4871
Max Act: 4.9871. Min Act: -0.1700
Data Index: 2871677 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4871. Min Range: -5.4871
Max Act: 4.9871. Min Act: -0.1700
Data Index: 3237879 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4871. Min Range: -5.4871
Max Act: 4.9871. Min Act: -0.1700
Data Index: 1782679 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4871. Min Range: -5.4871
Max Act: 4.9246. Min Act: -0.1700
Data Index: 7334303 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4871. Min Range: -5.4871
Max Act: 4.9558. Min Act: -0.1700
Data Index: 5201279 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4871. Min Range: -5.4871
Max Act: 4.9558. Min Act: -0.1700
Data Index: 1249436 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4871. Min Range: -5.4871
Max Act: 4.9558. Min Act: -0.1700
Data Index: 5375339 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4871. Min Range: -5.4871
Max Act: 4.9558. Min Act: -0.1700
Data Index: 48574 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19