Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4146 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.4320. Min Act: -0.1700
Data Index: 4096094 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.4320. Min Act: -0.1700
Data Index: 5308202 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.4320. Min Act: -0.1700
Data Index: 1083429 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.3695. Min Act: -0.1700
Data Index: 7138359 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.3070. Min Act: -0.1700
Data Index: 8320026 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.3070. Min Act: -0.1700
Data Index: 7406940 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.2757. Min Act: -0.1700
Data Index: 5153054 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.3070. Min Act: -0.1700
Data Index: 8692797 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.2757. Min Act: -0.1700
Data Index: 6400162 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.2445. Min Act: -0.1700
Data Index: 1080793 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.2445. Min Act: -0.1700
Data Index: 8044770 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.2132. Min Act: -0.1700
Data Index: 8452238 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.2132. Min Act: -0.1700
Data Index: 876431 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.2132. Min Act: -0.1700
Data Index: 7881641 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.2132. Min Act: -0.1700
Data Index: 4487481 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.1820. Min Act: -0.1700
Data Index: 395289 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.1820. Min Act: -0.1700
Data Index: 2293688 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.2132. Min Act: -0.1700
Data Index: 3272224 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.1820. Min Act: -0.1700
Data Index: 1168546 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4320. Min Range: -5.4320
Max Act: 5.1820. Min Act: -0.1700
Data Index: 2952507 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19