Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6144 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.4005. Min Act: -0.1700
Data Index: 4796004 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.3693. Min Act: -0.1700
Data Index: 429963 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.3380. Min Act: -0.1700
Data Index: 4361119 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.2755. Min Act: -0.1700
Data Index: 7041672 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.2130. Min Act: -0.1700
Data Index: 947103 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.2130. Min Act: -0.1700
Data Index: 8534235 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.1817. Min Act: -0.1700
Data Index: 3871976 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.1817. Min Act: -0.1700
Data Index: 7886360 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.1505. Min Act: -0.1700
Data Index: 4905402 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.1505. Min Act: -0.1700
Data Index: 7437275 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.0880. Min Act: -0.1700
Data Index: 2820363 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.0567. Min Act: -0.1700
Data Index: 3103019 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.0567. Min Act: -0.1700
Data Index: 5337961 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.0567. Min Act: -0.1700
Data Index: 7854814 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.0880. Min Act: -0.1700
Data Index: 4913484 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.0567. Min Act: -0.1700
Data Index: 4351113 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.0880. Min Act: -0.1700
Data Index: 7110388 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.0567. Min Act: -0.1700
Data Index: 323320 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.0567. Min Act: -0.1700
Data Index: 6550473 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4005. Min Range: -4.4005
Max Act: 4.0255. Min Act: -0.1700
Data Index: 5950766 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19