Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4032 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3362. Min Range: -7.3362
Max Act: 7.3362. Min Act: -0.1700
Data Index: 3453526 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3362. Min Range: -7.3362
Max Act: 7.2112. Min Act: -0.1700
Data Index: 2129089 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3362. Min Range: -7.3362
Max Act: 7.1487. Min Act: -0.1700
Data Index: 4464802 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3362. Min Range: -7.3362
Max Act: 7.0862. Min Act: -0.1700
Data Index: 4503974 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3362. Min Range: -7.3362
Max Act: 7.1487. Min Act: -0.1700
Data Index: 4163061 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3362. Min Range: -7.3362
Max Act: 7.0862. Min Act: -0.1700
Data Index: 6331628 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3362. Min Range: -7.3362
Max Act: 6.9924. Min Act: -0.1700
Data Index: 1542647 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3362. Min Range: -7.3362
Max Act: 6.9612. Min Act: -0.1700
Data Index: 4163052 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3362. Min Range: -7.3362
Max Act: 6.9612. Min Act: -0.1700
Data Index: 4471338 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3362. Min Range: -7.3362
Max Act: 6.9299. Min Act: -0.1700
Data Index: 1706738 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3362. Min Range: -7.3362
Max Act: 6.9299. Min Act: -0.1700
Data Index: 3002348 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3362. Min Range: -7.3362
Max Act: 6.9299. Min Act: -0.1700
Data Index: 4847612 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3362. Min Range: -7.3362
Max Act: 6.8674. Min Act: -0.1700
Data Index: 2876761 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3362. Min Range: -7.3362
Max Act: 6.8362. Min Act: -0.1700
Data Index: 4435966 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3362. Min Range: -7.3362
Max Act: 6.8674. Min Act: -0.1700
Data Index: 893558 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3362. Min Range: -7.3362
Max Act: 6.8362. Min Act: -0.1700
Data Index: 6642903 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3362. Min Range: -7.3362
Max Act: 6.8049. Min Act: -0.1700
Data Index: 2531444 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3362. Min Range: -7.3362
Max Act: 6.8049. Min Act: -0.1700
Data Index: 5222487 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3362. Min Range: -7.3362
Max Act: 6.8049. Min Act: -0.1700
Data Index: 8201928 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3362. Min Range: -7.3362
Max Act: 6.8049. Min Act: -0.1700
Data Index: 177055 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19