Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 66 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.8514. Min Act: -0.1700
Data Index: 8406310 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.8201. Min Act: -0.1700
Data Index: 158088 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.8201. Min Act: -0.1700
Data Index: 7318029 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.7576. Min Act: -0.1700
Data Index: 1094940 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.7889. Min Act: -0.1700
Data Index: 5807197 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.7576. Min Act: -0.1700
Data Index: 1144051 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.6639. Min Act: -0.1700
Data Index: 158087 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.6639. Min Act: -0.1700
Data Index: 5349156 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.6639. Min Act: -0.1700
Data Index: 5349160 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.6326. Min Act: -0.1700
Data Index: 1459575 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.6326. Min Act: -0.1700
Data Index: 8009393 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.6014. Min Act: -0.1700
Data Index: 8257799 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.6014. Min Act: -0.1700
Data Index: 40073 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.6014. Min Act: -0.1700
Data Index: 2340436 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.5701. Min Act: -0.1700
Data Index: 2925506 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.5701. Min Act: -0.1700
Data Index: 32544 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.5701. Min Act: -0.1700
Data Index: 6975456 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.6014. Min Act: -0.1700
Data Index: 8118276 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.5076. Min Act: -0.1700
Data Index: 8043280 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8514. Min Range: -5.8514
Max Act: 5.5389. Min Act: -0.1700
Data Index: 8060188 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19