Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4023 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3742. Min Range: -3.3742
Max Act: 3.3742. Min Act: -0.1700
Data Index: 5599039 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3742. Min Range: -3.3742
Max Act: 3.2171. Min Act: -0.1700
Data Index: 5679407 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3742. Min Range: -3.3742
Max Act: 3.1857. Min Act: -0.1700
Data Index: 7401101 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3742. Min Range: -3.3742
Max Act: 3.1227. Min Act: -0.1700
Data Index: 836760 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3742. Min Range: -3.3742
Max Act: 3.1385. Min Act: -0.1700
Data Index: 5994988 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3742. Min Range: -3.3742
Max Act: 3.1227. Min Act: -0.1700
Data Index: 2853999 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3742. Min Range: -3.3742
Max Act: 3.1227. Min Act: -0.1700
Data Index: 3027315 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3742. Min Range: -3.3742
Max Act: 3.0597. Min Act: -0.1700
Data Index: 6925985 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3742. Min Range: -3.3742
Max Act: 2.9965. Min Act: -0.1700
Data Index: 8299357 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3742. Min Range: -3.3742
Max Act: 3.0439. Min Act: -0.1700
Data Index: 4817733 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3742. Min Range: -3.3742
Max Act: 3.0281. Min Act: -0.1700
Data Index: 376519 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3742. Min Range: -3.3742
Max Act: 3.0281. Min Act: -0.1700
Data Index: 7952890 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3742. Min Range: -3.3742
Max Act: 3.0281. Min Act: -0.1700
Data Index: 5368000 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3742. Min Range: -3.3742
Max Act: 3.0281. Min Act: -0.1700
Data Index: 8391341 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3742. Min Range: -3.3742
Max Act: 2.9807. Min Act: -0.1700
Data Index: 7410137 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3742. Min Range: -3.3742
Max Act: 2.9807. Min Act: -0.1700
Data Index: 96378 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3742. Min Range: -3.3742
Max Act: 2.9965. Min Act: -0.1700
Data Index: 4576781 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3742. Min Range: -3.3742
Max Act: 2.9965. Min Act: -0.1700
Data Index: 2306219 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3742. Min Range: -3.3742
Max Act: 2.9807. Min Act: -0.1700
Data Index: 5688388 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3742. Min Range: -3.3742
Max Act: 2.9332. Min Act: -0.1700
Data Index: 5458384 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19