Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1417 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2743. Min Range: -7.2743
Max Act: 7.2743. Min Act: -0.1700
Data Index: 5586469 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2743. Min Range: -7.2743
Max Act: 7.0243. Min Act: -0.1700
Data Index: 3883338 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.9618. Min Act: -0.1700
Data Index: 949933 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.9305. Min Act: -0.1700
Data Index: 7008019 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.8368. Min Act: -0.1700
Data Index: 7814064 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.8368. Min Act: -0.1700
Data Index: 950156 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.6805. Min Act: -0.1700
Data Index: 8637319 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.5868. Min Act: -0.1700
Data Index: 8434132 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.6180. Min Act: -0.1700
Data Index: 3397480 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.5555. Min Act: -0.1700
Data Index: 1513853 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.4930. Min Act: -0.1700
Data Index: 8044155 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.5243. Min Act: -0.1700
Data Index: 2508531 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.5243. Min Act: -0.1700
Data Index: 2366970 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.4618. Min Act: -0.1700
Data Index: 6193961 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.4618. Min Act: -0.1700
Data Index: 1917980 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.4618. Min Act: -0.1700
Data Index: 845020 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.4618. Min Act: -0.1700
Data Index: 7815438 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.4618. Min Act: -0.1700
Data Index: 1515906 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.4618. Min Act: -0.1700
Data Index: 4833140 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.4305. Min Act: -0.1700
Data Index: 7029171 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19