Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1206 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2523. Min Range: -8.2523
Max Act: 8.2523. Min Act: -0.1700
Data Index: 5435713 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2523. Min Range: -8.2523
Max Act: 7.0336. Min Act: -0.1700
Data Index: 3502971 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2523. Min Range: -8.2523
Max Act: 6.9086. Min Act: -0.1700
Data Index: 8247516 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2523. Min Range: -8.2523
Max Act: 6.8461. Min Act: -0.1700
Data Index: 7482295 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2523. Min Range: -8.2523
Max Act: 6.7836. Min Act: -0.1700
Data Index: 720711 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2523. Min Range: -8.2523
Max Act: 6.7836. Min Act: -0.1700
Data Index: 3322316 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2523. Min Range: -8.2523
Max Act: 6.7211. Min Act: -0.1700
Data Index: 3189094 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2523. Min Range: -8.2523
Max Act: 6.7211. Min Act: -0.1700
Data Index: 8110591 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2523. Min Range: -8.2523
Max Act: 6.7211. Min Act: -0.1700
Data Index: 8538328 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2523. Min Range: -8.2523
Max Act: 6.6898. Min Act: -0.1700
Data Index: 173598 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2523. Min Range: -8.2523
Max Act: 6.6898. Min Act: -0.1700
Data Index: 6517601 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2523. Min Range: -8.2523
Max Act: 6.6586. Min Act: -0.1700
Data Index: 8538317 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2523. Min Range: -8.2523
Max Act: 6.6586. Min Act: -0.1700
Data Index: 8783643 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2523. Min Range: -8.2523
Max Act: 6.6273. Min Act: -0.1700
Data Index: 4896897 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2523. Min Range: -8.2523
Max Act: 6.5648. Min Act: -0.1700
Data Index: 2755410 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2523. Min Range: -8.2523
Max Act: 6.5648. Min Act: -0.1700
Data Index: 1098856 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2523. Min Range: -8.2523
Max Act: 6.5648. Min Act: -0.1700
Data Index: 4064081 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2523. Min Range: -8.2523
Max Act: 6.5336. Min Act: -0.1700
Data Index: 8274365 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2523. Min Range: -8.2523
Max Act: 6.5336. Min Act: -0.1700
Data Index: 5889081 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2523. Min Range: -8.2523
Max Act: 6.5336. Min Act: -0.1700
Data Index: 2319535 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19