Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6386 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.9471. Min Act: -0.1700
Data Index: 372770 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.9158. Min Act: -0.1700
Data Index: 1560832 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.8533. Min Act: -0.1700
Data Index: 7527033 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.8221. Min Act: -0.1700
Data Index: 3064376 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.7596. Min Act: -0.1700
Data Index: 461906 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.6971. Min Act: -0.1700
Data Index: 5800261 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.6658. Min Act: -0.1700
Data Index: 1203155 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.6658. Min Act: -0.1700
Data Index: 3366842 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.6971. Min Act: -0.1700
Data Index: 7380437 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.6346. Min Act: -0.1700
Data Index: 8126530 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.6346. Min Act: -0.1700
Data Index: 7449096 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.6033. Min Act: -0.1700
Data Index: 3139888 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.5096. Min Act: -0.1700
Data Index: 6453622 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.5408. Min Act: -0.1700
Data Index: 962090 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.5096. Min Act: -0.1700
Data Index: 800951 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.4783. Min Act: -0.1700
Data Index: 637170 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.5096. Min Act: -0.1700
Data Index: 6985432 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.4783. Min Act: -0.1700
Data Index: 748445 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.4471. Min Act: -0.1700
Data Index: 7243386 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9471. Min Range: -6.9471
Max Act: 6.4471. Min Act: -0.1700
Data Index: 1157310 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19