Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4007 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.8604. Min Act: -0.1700
Data Index: 2312493 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.5167. Min Act: -0.1700
Data Index: 513353 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.5479. Min Act: -0.1700
Data Index: 421365 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.5167. Min Act: -0.1700
Data Index: 8671698 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.4854. Min Act: -0.1700
Data Index: 8114043 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.4854. Min Act: -0.1700
Data Index: 394081 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.4229. Min Act: -0.1700
Data Index: 347966 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.4229. Min Act: -0.1700
Data Index: 3355180 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.3917. Min Act: -0.1700
Data Index: 458278 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.3917. Min Act: -0.1700
Data Index: 8224937 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.3292. Min Act: -0.1700
Data Index: 2555532 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.3917. Min Act: -0.1700
Data Index: 6467984 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.3604. Min Act: -0.1700
Data Index: 6004276 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.3292. Min Act: -0.1700
Data Index: 3807630 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.3604. Min Act: -0.1700
Data Index: 1547132 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.3292. Min Act: -0.1700
Data Index: 2518499 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.3292. Min Act: -0.1700
Data Index: 1234418 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.2979. Min Act: -0.1700
Data Index: 2987626 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.2979. Min Act: -0.1700
Data Index: 183277 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8604. Min Range: -5.8604
Max Act: 5.2979. Min Act: -0.1700
Data Index: 4652835 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19