Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2142 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7597. Min Range: -10.7597
Max Act: 10.7597. Min Act: -0.1700
Data Index: 1998246 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7597. Min Range: -10.7597
Max Act: 10.6972. Min Act: -0.1700
Data Index: 6437587 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7597. Min Range: -10.7597
Max Act: 10.6347. Min Act: -0.1700
Data Index: 5744662 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7597. Min Range: -10.7597
Max Act: 10.5722. Min Act: -0.1700
Data Index: 6976465 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7597. Min Range: -10.7597
Max Act: 10.3222. Min Act: -0.1700
Data Index: 818633 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7597. Min Range: -10.7597
Max Act: 10.1972. Min Act: -0.1700
Data Index: 7768984 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7597. Min Range: -10.7597
Max Act: 10.1972. Min Act: -0.1700
Data Index: 1476042 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7597. Min Range: -10.7597
Max Act: 10.0722. Min Act: -0.1700
Data Index: 1360872 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7597. Min Range: -10.7597
Max Act: 10.0097. Min Act: -0.1700
Data Index: 7016849 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7597. Min Range: -10.7597
Max Act: 9.9472. Min Act: -0.1700
Data Index: 4958927 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7597. Min Range: -10.7597
Max Act: 9.9472. Min Act: -0.1700
Data Index: 6993475 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7597. Min Range: -10.7597
Max Act: 9.9472. Min Act: -0.1700
Data Index: 7237929 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7597. Min Range: -10.7597
Max Act: 9.9472. Min Act: -0.1700
Data Index: 7806380 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7597. Min Range: -10.7597
Max Act: 9.8847. Min Act: -0.1700
Data Index: 42953 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7597. Min Range: -10.7597
Max Act: 9.8222. Min Act: -0.1700
Data Index: 339735 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7597. Min Range: -10.7597
Max Act: 9.8222. Min Act: -0.1700
Data Index: 5916950 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7597. Min Range: -10.7597
Max Act: 9.7597. Min Act: -0.1700
Data Index: 3560069 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7597. Min Range: -10.7597
Max Act: 9.7597. Min Act: -0.1700
Data Index: 2991570 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7597. Min Range: -10.7597
Max Act: 9.6972. Min Act: -0.1700
Data Index: 6420853 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7597. Min Range: -10.7597
Max Act: 9.6972. Min Act: -0.1700
Data Index: 7219122 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19