Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3920 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4079. Min Range: -6.4079
Max Act: 6.4079. Min Act: -0.1700
Data Index: 5435573 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4079. Min Range: -6.4079
Max Act: 6.1579. Min Act: -0.1700
Data Index: 861944 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4079. Min Range: -6.4079
Max Act: 6.1267. Min Act: -0.1700
Data Index: 8489755 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4079. Min Range: -6.4079
Max Act: 6.0954. Min Act: -0.1700
Data Index: 8680444 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4079. Min Range: -6.4079
Max Act: 5.9704. Min Act: -0.1700
Data Index: 7343665 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4079. Min Range: -6.4079
Max Act: 6.0642. Min Act: -0.1700
Data Index: 1167716 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4079. Min Range: -6.4079
Max Act: 6.0642. Min Act: -0.1700
Data Index: 8728519 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4079. Min Range: -6.4079
Max Act: 6.0017. Min Act: -0.1700
Data Index: 1529010 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4079. Min Range: -6.4079
Max Act: 5.9704. Min Act: -0.1700
Data Index: 4667685 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4079. Min Range: -6.4079
Max Act: 5.9704. Min Act: -0.1700
Data Index: 5548630 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4079. Min Range: -6.4079
Max Act: 5.9392. Min Act: -0.1700
Data Index: 1976433 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4079. Min Range: -6.4079
Max Act: 5.9392. Min Act: -0.1700
Data Index: 2769610 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4079. Min Range: -6.4079
Max Act: 5.9392. Min Act: -0.1700
Data Index: 7018256 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4079. Min Range: -6.4079
Max Act: 5.9392. Min Act: -0.1700
Data Index: 8092240 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4079. Min Range: -6.4079
Max Act: 5.9079. Min Act: -0.1700
Data Index: 7211150 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4079. Min Range: -6.4079
Max Act: 5.8767. Min Act: -0.1700
Data Index: 7856210 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4079. Min Range: -6.4079
Max Act: 5.9079. Min Act: -0.1700
Data Index: 7401219 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4079. Min Range: -6.4079
Max Act: 5.9079. Min Act: -0.1700
Data Index: 32640 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4079. Min Range: -6.4079
Max Act: 5.8767. Min Act: -0.1700
Data Index: 2028484 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4079. Min Range: -6.4079
Max Act: 5.9079. Min Act: -0.1700
Data Index: 4306022 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19