Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4476 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.9594. Min Act: -0.1700
Data Index: 2948059 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.8344. Min Act: -0.1700
Data Index: 1973216 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.7719. Min Act: -0.1700
Data Index: 5573122 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.7719. Min Act: -0.1700
Data Index: 234236 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.7094. Min Act: -0.1700
Data Index: 5633790 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.7406. Min Act: -0.1700
Data Index: 5723113 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.7406. Min Act: -0.1700
Data Index: 102554 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.7406. Min Act: -0.1700
Data Index: 301067 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.7406. Min Act: -0.1700
Data Index: 8079773 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.7406. Min Act: -0.1700
Data Index: 4459194 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.6781. Min Act: -0.1700
Data Index: 8692618 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.6781. Min Act: -0.1700
Data Index: 6223725 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.6781. Min Act: -0.1700
Data Index: 4975076 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.6781. Min Act: -0.1700
Data Index: 4469573 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.6469. Min Act: -0.1700
Data Index: 5422558 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.6156. Min Act: -0.1700
Data Index: 7198580 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.6156. Min Act: -0.1700
Data Index: 6378718 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.6469. Min Act: -0.1700
Data Index: 6047967 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.6781. Min Act: -0.1700
Data Index: 3079964 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9594. Min Range: -5.9594
Max Act: 5.6156. Min Act: -0.1700
Data Index: 3494575 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19