Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 870 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3656. Min Range: -6.3656
Max Act: 6.3656. Min Act: -0.1700
Data Index: 5516688 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3656. Min Range: -6.3656
Max Act: 6.1156. Min Act: -0.1700
Data Index: 1759409 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3656. Min Range: -6.3656
Max Act: 6.0843. Min Act: -0.1700
Data Index: 3683385 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3656. Min Range: -6.3656
Max Act: 6.0531. Min Act: -0.1700
Data Index: 1279760 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3656. Min Range: -6.3656
Max Act: 5.9906. Min Act: -0.1700
Data Index: 6961374 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3656. Min Range: -6.3656
Max Act: 5.9593. Min Act: -0.1700
Data Index: 3130741 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3656. Min Range: -6.3656
Max Act: 5.9281. Min Act: -0.1700
Data Index: 6722775 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3656. Min Range: -6.3656
Max Act: 5.9593. Min Act: -0.1700
Data Index: 669079 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3656. Min Range: -6.3656
Max Act: 5.8656. Min Act: -0.1700
Data Index: 5256764 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3656. Min Range: -6.3656
Max Act: 5.8656. Min Act: -0.1700
Data Index: 134944 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3656. Min Range: -6.3656
Max Act: 5.8343. Min Act: -0.1700
Data Index: 6199672 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3656. Min Range: -6.3656
Max Act: 5.8656. Min Act: -0.1700
Data Index: 15157 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3656. Min Range: -6.3656
Max Act: 5.8031. Min Act: -0.1700
Data Index: 5982067 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3656. Min Range: -6.3656
Max Act: 5.8343. Min Act: -0.1700
Data Index: 276174 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3656. Min Range: -6.3656
Max Act: 5.8031. Min Act: -0.1700
Data Index: 3396479 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3656. Min Range: -6.3656
Max Act: 5.8031. Min Act: -0.1700
Data Index: 7973171 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3656. Min Range: -6.3656
Max Act: 5.8343. Min Act: -0.1700
Data Index: 7500131 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3656. Min Range: -6.3656
Max Act: 5.8031. Min Act: -0.1700
Data Index: 4585008 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3656. Min Range: -6.3656
Max Act: 5.7718. Min Act: -0.1700
Data Index: 1033930 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3656. Min Range: -6.3656
Max Act: 5.7718. Min Act: -0.1700
Data Index: 7488973 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19