Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3627 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8200. Min Range: -6.8200
Max Act: 6.8200. Min Act: -0.1700
Data Index: 3470945 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8200. Min Range: -6.8200
Max Act: 6.7262. Min Act: -0.1700
Data Index: 3298465 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8200. Min Range: -6.8200
Max Act: 6.4762. Min Act: -0.1700
Data Index: 4033026 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8200. Min Range: -6.8200
Max Act: 6.4137. Min Act: -0.1700
Data Index: 7257246 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8200. Min Range: -6.8200
Max Act: 6.3825. Min Act: -0.1700
Data Index: 7178622 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8200. Min Range: -6.8200
Max Act: 6.3512. Min Act: -0.1700
Data Index: 1661565 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8200. Min Range: -6.8200
Max Act: 6.3200. Min Act: -0.1700
Data Index: 2100228 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8200. Min Range: -6.8200
Max Act: 6.1950. Min Act: -0.1700
Data Index: 7561972 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8200. Min Range: -6.8200
Max Act: 6.1950. Min Act: -0.1700
Data Index: 1132417 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8200. Min Range: -6.8200
Max Act: 6.1325. Min Act: -0.1700
Data Index: 976386 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8200. Min Range: -6.8200
Max Act: 6.0700. Min Act: -0.1700
Data Index: 7381306 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8200. Min Range: -6.8200
Max Act: 6.0700. Min Act: -0.1700
Data Index: 8305931 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8200. Min Range: -6.8200
Max Act: 6.0700. Min Act: -0.1700
Data Index: 1337903 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8200. Min Range: -6.8200
Max Act: 6.0700. Min Act: -0.1700
Data Index: 5521242 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8200. Min Range: -6.8200
Max Act: 6.0387. Min Act: -0.1700
Data Index: 5274215 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8200. Min Range: -6.8200
Max Act: 6.0075. Min Act: -0.1700
Data Index: 4574047 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8200. Min Range: -6.8200
Max Act: 6.0075. Min Act: -0.1700
Data Index: 7360865 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8200. Min Range: -6.8200
Max Act: 6.0075. Min Act: -0.1700
Data Index: 642620 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8200. Min Range: -6.8200
Max Act: 5.9762. Min Act: -0.1700
Data Index: 7133020 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8200. Min Range: -6.8200
Max Act: 5.9762. Min Act: -0.1700
Data Index: 6318105 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19