Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4095 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0224. Min Range: -6.0224
Max Act: 6.0224. Min Act: -0.1700
Data Index: 5543212 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0224. Min Range: -6.0224
Max Act: 5.6474. Min Act: -0.1700
Data Index: 3880732 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0224. Min Range: -6.0224
Max Act: 5.4599. Min Act: -0.1700
Data Index: 8703127 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0224. Min Range: -6.0224
Max Act: 5.4287. Min Act: -0.1700
Data Index: 7991333 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0224. Min Range: -6.0224
Max Act: 5.3974. Min Act: -0.1700
Data Index: 5981754 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0224. Min Range: -6.0224
Max Act: 5.3974. Min Act: -0.1700
Data Index: 2025452 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0224. Min Range: -6.0224
Max Act: 5.3349. Min Act: -0.1700
Data Index: 7281328 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0224. Min Range: -6.0224
Max Act: 5.3349. Min Act: -0.1700
Data Index: 187731 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0224. Min Range: -6.0224
Max Act: 5.2412. Min Act: -0.1700
Data Index: 2375726 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0224. Min Range: -6.0224
Max Act: 5.2412. Min Act: -0.1700
Data Index: 3469551 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0224. Min Range: -6.0224
Max Act: 5.2412. Min Act: -0.1700
Data Index: 2145035 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0224. Min Range: -6.0224
Max Act: 5.1787. Min Act: -0.1700
Data Index: 3155488 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0224. Min Range: -6.0224
Max Act: 5.1787. Min Act: -0.1700
Data Index: 2688493 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0224. Min Range: -6.0224
Max Act: 5.1787. Min Act: -0.1700
Data Index: 432490 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0224. Min Range: -6.0224
Max Act: 5.1474. Min Act: -0.1700
Data Index: 1419961 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0224. Min Range: -6.0224
Max Act: 5.1474. Min Act: -0.1700
Data Index: 6286711 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0224. Min Range: -6.0224
Max Act: 5.1474. Min Act: -0.1700
Data Index: 3452026 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0224. Min Range: -6.0224
Max Act: 5.1474. Min Act: -0.1700
Data Index: 8750450 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0224. Min Range: -6.0224
Max Act: 5.1162. Min Act: -0.1700
Data Index: 2607326 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0224. Min Range: -6.0224
Max Act: 5.0849. Min Act: -0.1700
Data Index: 1974407 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19