Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5166. Min Range: -5.5166
Max Act: 5.5166. Min Act: -0.1700
Data Index: 4115360 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5166. Min Range: -5.5166
Max Act: 5.3916. Min Act: -0.1700
Data Index: 333296 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5166. Min Range: -5.5166
Max Act: 5.2666. Min Act: -0.1700
Data Index: 5103602 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5166. Min Range: -5.5166
Max Act: 5.2353. Min Act: -0.1700
Data Index: 678849 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5166. Min Range: -5.5166
Max Act: 5.1728. Min Act: -0.1700
Data Index: 3896561 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5166. Min Range: -5.5166
Max Act: 5.0478. Min Act: -0.1700
Data Index: 4510606 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5166. Min Range: -5.5166
Max Act: 5.0166. Min Act: -0.1700
Data Index: 4683229 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5166. Min Range: -5.5166
Max Act: 4.9853. Min Act: -0.1700
Data Index: 283411 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5166. Min Range: -5.5166
Max Act: 4.9853. Min Act: -0.1700
Data Index: 5946926 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5166. Min Range: -5.5166
Max Act: 4.9228. Min Act: -0.1700
Data Index: 2729152 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5166. Min Range: -5.5166
Max Act: 4.9228. Min Act: -0.1700
Data Index: 3424178 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5166. Min Range: -5.5166
Max Act: 4.8916. Min Act: -0.1700
Data Index: 3540913 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5166. Min Range: -5.5166
Max Act: 4.8603. Min Act: -0.1700
Data Index: 6097225 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5166. Min Range: -5.5166
Max Act: 4.8916. Min Act: -0.1700
Data Index: 5996194 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5166. Min Range: -5.5166
Max Act: 4.8916. Min Act: -0.1700
Data Index: 7740672 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5166. Min Range: -5.5166
Max Act: 4.8916. Min Act: -0.1700
Data Index: 3861908 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5166. Min Range: -5.5166
Max Act: 4.8603. Min Act: -0.1700
Data Index: 588751 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5166. Min Range: -5.5166
Max Act: 4.7978. Min Act: -0.1700
Data Index: 4779072 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5166. Min Range: -5.5166
Max Act: 4.8291. Min Act: -0.1700
Data Index: 8473192 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5166. Min Range: -5.5166
Max Act: 4.7978. Min Act: -0.1700
Data Index: 988249 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19