Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3263 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8094. Min Range: -6.8094
Max Act: 6.8094. Min Act: -0.1700
Data Index: 6631199 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8094. Min Range: -6.8094
Max Act: 6.3719. Min Act: -0.1700
Data Index: 4871165 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8094. Min Range: -6.8094
Max Act: 6.2469. Min Act: -0.1700
Data Index: 6465160 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8094. Min Range: -6.8094
Max Act: 6.2156. Min Act: -0.1700
Data Index: 3773017 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8094. Min Range: -6.8094
Max Act: 6.2469. Min Act: -0.1700
Data Index: 272033 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8094. Min Range: -6.8094
Max Act: 6.1844. Min Act: -0.1700
Data Index: 5671882 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8094. Min Range: -6.8094
Max Act: 6.1531. Min Act: -0.1700
Data Index: 4349509 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8094. Min Range: -6.8094
Max Act: 6.0594. Min Act: -0.1700
Data Index: 3083695 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8094. Min Range: -6.8094
Max Act: 6.0281. Min Act: -0.1700
Data Index: 8744652 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8094. Min Range: -6.8094
Max Act: 6.0281. Min Act: -0.1700
Data Index: 2307782 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8094. Min Range: -6.8094
Max Act: 5.9656. Min Act: -0.1700
Data Index: 5984229 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8094. Min Range: -6.8094
Max Act: 5.9344. Min Act: -0.1700
Data Index: 5694785 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8094. Min Range: -6.8094
Max Act: 5.9344. Min Act: -0.1700
Data Index: 4687451 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8094. Min Range: -6.8094
Max Act: 5.9031. Min Act: -0.1700
Data Index: 3323265 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8094. Min Range: -6.8094
Max Act: 5.9344. Min Act: -0.1700
Data Index: 6331461 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8094. Min Range: -6.8094
Max Act: 5.9656. Min Act: -0.1700
Data Index: 2019585 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8094. Min Range: -6.8094
Max Act: 5.9031. Min Act: -0.1700
Data Index: 5367518 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8094. Min Range: -6.8094
Max Act: 5.8719. Min Act: -0.1700
Data Index: 811736 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8094. Min Range: -6.8094
Max Act: 5.8406. Min Act: -0.1700
Data Index: 8675995 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8094. Min Range: -6.8094
Max Act: 5.8094. Min Act: -0.1700
Data Index: 4407751 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19