Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1656 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.7656. Min Act: -0.1700
Data Index: 6388559 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.7031. Min Act: -0.1700
Data Index: 3227311 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.5156. Min Act: -0.1700
Data Index: 3923058 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.3906. Min Act: -0.1700
Data Index: 4778354 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.4219. Min Act: -0.1700
Data Index: 3639563 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.3594. Min Act: -0.1700
Data Index: 7921253 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.3281. Min Act: -0.1700
Data Index: 2965575 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.2969. Min Act: -0.1700
Data Index: 612810 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.3281. Min Act: -0.1700
Data Index: 893017 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.2656. Min Act: -0.1700
Data Index: 8106349 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.2969. Min Act: -0.1700
Data Index: 2676074 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.2969. Min Act: -0.1700
Data Index: 5757625 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.2656. Min Act: -0.1700
Data Index: 6635569 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.2656. Min Act: -0.1700
Data Index: 926887 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.2656. Min Act: -0.1700
Data Index: 4708598 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.2344. Min Act: -0.1700
Data Index: 6374000 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.2031. Min Act: -0.1700
Data Index: 5634496 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.2344. Min Act: -0.1700
Data Index: 6958340 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.2031. Min Act: -0.1700
Data Index: 6335324 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7656. Min Range: -6.7656
Max Act: 6.2031. Min Act: -0.1700
Data Index: 4516552 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19