Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3940 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2229. Min Range: -6.2229
Max Act: 6.2229. Min Act: -0.1700
Data Index: 3327545 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2229. Min Range: -6.2229
Max Act: 6.0354. Min Act: -0.1700
Data Index: 5554436 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2229. Min Range: -6.2229
Max Act: 5.9729. Min Act: -0.1700
Data Index: 3632244 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2229. Min Range: -6.2229
Max Act: 5.9729. Min Act: -0.1700
Data Index: 5526631 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2229. Min Range: -6.2229
Max Act: 5.8791. Min Act: -0.1700
Data Index: 6585443 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2229. Min Range: -6.2229
Max Act: 5.9416. Min Act: -0.1700
Data Index: 5686287 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2229. Min Range: -6.2229
Max Act: 5.9104. Min Act: -0.1700
Data Index: 4271463 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2229. Min Range: -6.2229
Max Act: 5.8791. Min Act: -0.1700
Data Index: 6822411 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2229. Min Range: -6.2229
Max Act: 5.8479. Min Act: -0.1700
Data Index: 665794 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2229. Min Range: -6.2229
Max Act: 5.8791. Min Act: -0.1700
Data Index: 6972126 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2229. Min Range: -6.2229
Max Act: 5.8791. Min Act: -0.1700
Data Index: 1518836 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2229. Min Range: -6.2229
Max Act: 5.8479. Min Act: -0.1700
Data Index: 4119532 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2229. Min Range: -6.2229
Max Act: 5.8166. Min Act: -0.1700
Data Index: 2638040 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2229. Min Range: -6.2229
Max Act: 5.7854. Min Act: -0.1700
Data Index: 7700005 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2229. Min Range: -6.2229
Max Act: 5.8166. Min Act: -0.1700
Data Index: 1493160 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2229. Min Range: -6.2229
Max Act: 5.7854. Min Act: -0.1700
Data Index: 4494928 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2229. Min Range: -6.2229
Max Act: 5.7541. Min Act: -0.1700
Data Index: 69773 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2229. Min Range: -6.2229
Max Act: 5.7541. Min Act: -0.1700
Data Index: 4505336 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2229. Min Range: -6.2229
Max Act: 5.7854. Min Act: -0.1700
Data Index: 670306 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2229. Min Range: -6.2229
Max Act: 5.7854. Min Act: -0.1700
Data Index: 3938442 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19