Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4855 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8108. Min Range: -10.8108
Max Act: 10.8108. Min Act: -0.1700
Data Index: 4582137 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8108. Min Range: -10.8108
Max Act: 10.4358. Min Act: -0.1700
Data Index: 3381539 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8108. Min Range: -10.8108
Max Act: 10.3108. Min Act: -0.1700
Data Index: 6613451 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8108. Min Range: -10.8108
Max Act: 10.2483. Min Act: -0.1700
Data Index: 4829773 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8108. Min Range: -10.8108
Max Act: 10.2483. Min Act: -0.1700
Data Index: 2834027 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8108. Min Range: -10.8108
Max Act: 10.1858. Min Act: -0.1700
Data Index: 7198878 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8108. Min Range: -10.8108
Max Act: 10.1858. Min Act: -0.1700
Data Index: 5499678 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8108. Min Range: -10.8108
Max Act: 10.1233. Min Act: -0.1700
Data Index: 7815519 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8108. Min Range: -10.8108
Max Act: 10.1233. Min Act: -0.1700
Data Index: 5544031 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8108. Min Range: -10.8108
Max Act: 9.9358. Min Act: -0.1700
Data Index: 2464199 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8108. Min Range: -10.8108
Max Act: 9.9983. Min Act: -0.1700
Data Index: 2454766 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8108. Min Range: -10.8108
Max Act: 9.9983. Min Act: -0.1700
Data Index: 8310054 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8108. Min Range: -10.8108
Max Act: 9.9358. Min Act: -0.1700
Data Index: 8429185 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8108. Min Range: -10.8108
Max Act: 9.9358. Min Act: -0.1700
Data Index: 8205723 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8108. Min Range: -10.8108
Max Act: 9.9983. Min Act: -0.1700
Data Index: 3115114 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8108. Min Range: -10.8108
Max Act: 9.8733. Min Act: -0.1700
Data Index: 1738017 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8108. Min Range: -10.8108
Max Act: 9.8733. Min Act: -0.1700
Data Index: 6519599 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8108. Min Range: -10.8108
Max Act: 9.9358. Min Act: -0.1700
Data Index: 2197130 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8108. Min Range: -10.8108
Max Act: 9.8733. Min Act: -0.1700
Data Index: 6127292 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8108. Min Range: -10.8108
Max Act: 9.8733. Min Act: -0.1700
Data Index: 6039834 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19