Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6167 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.4176. Min Act: -0.1700
Data Index: 4957211 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.4489. Min Act: -0.1700
Data Index: 5917979 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.3239. Min Act: -0.1700
Data Index: 8287533 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.2926. Min Act: -0.1700
Data Index: 6741045 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.2926. Min Act: -0.1700
Data Index: 1639963 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.1989. Min Act: -0.1700
Data Index: 8065322 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.1989. Min Act: -0.1700
Data Index: 1681213 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.1676. Min Act: -0.1700
Data Index: 3158014 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.1676. Min Act: -0.1700
Data Index: 4593007 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.1364. Min Act: -0.1700
Data Index: 4107048 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.1364. Min Act: -0.1700
Data Index: 6007689 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.1364. Min Act: -0.1700
Data Index: 2837984 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.1364. Min Act: -0.1700
Data Index: 995000 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.1676. Min Act: -0.1700
Data Index: 2550729 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.1364. Min Act: -0.1700
Data Index: 8741165 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.1364. Min Act: -0.1700
Data Index: 1556572 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.0739. Min Act: -0.1700
Data Index: 3945307 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.0739. Min Act: -0.1700
Data Index: 3778434 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.0426. Min Act: -0.1700
Data Index: 5449028 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4489. Min Range: -6.4489
Max Act: 6.0739. Min Act: -0.1700
Data Index: 3138708 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19