Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3358 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.8556. Min Act: -0.1700
Data Index: 3162001 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.7931. Min Act: -0.1700
Data Index: 5660789 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.7931. Min Act: -0.1700
Data Index: 4890726 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.7306. Min Act: -0.1700
Data Index: 7644502 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.6994. Min Act: -0.1700
Data Index: 1579989 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.6056. Min Act: -0.1700
Data Index: 6958220 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.6056. Min Act: -0.1700
Data Index: 5976023 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.5744. Min Act: -0.1700
Data Index: 5729472 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.5431. Min Act: -0.1700
Data Index: 6756662 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.5119. Min Act: -0.1700
Data Index: 6949725 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.5119. Min Act: -0.1700
Data Index: 7917432 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.4806. Min Act: -0.1700
Data Index: 2213542 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.4806. Min Act: -0.1700
Data Index: 4776969 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.4494. Min Act: -0.1700
Data Index: 6345183 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.4494. Min Act: -0.1700
Data Index: 823513 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.4494. Min Act: -0.1700
Data Index: 5179855 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.4181. Min Act: -0.1700
Data Index: 7801028 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.4181. Min Act: -0.1700
Data Index: 3162746 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.4181. Min Act: -0.1700
Data Index: 33802 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8556. Min Range: -5.8556
Max Act: 5.4181. Min Act: -0.1700
Data Index: 4605703 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19