Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2446 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.8467. Min Act: -0.1700
Data Index: 2573215 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.7842. Min Act: -0.1700
Data Index: 6198406 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.7217. Min Act: -0.1700
Data Index: 5115757 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.6592. Min Act: -0.1700
Data Index: 2177475 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.6279. Min Act: -0.1700
Data Index: 5395896 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.6279. Min Act: -0.1700
Data Index: 6162174 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.5967. Min Act: -0.1700
Data Index: 2280431 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.6279. Min Act: -0.1700
Data Index: 729651 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.5654. Min Act: -0.1700
Data Index: 8001467 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.5342. Min Act: -0.1700
Data Index: 353131 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.5342. Min Act: -0.1700
Data Index: 1308380 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.5342. Min Act: -0.1700
Data Index: 8015182 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.5342. Min Act: -0.1700
Data Index: 6322151 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.5029. Min Act: -0.1700
Data Index: 2304686 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.5029. Min Act: -0.1700
Data Index: 6729411 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.5029. Min Act: -0.1700
Data Index: 1210309 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.5029. Min Act: -0.1700
Data Index: 6136938 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.4717. Min Act: -0.1700
Data Index: 7240176 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.4717. Min Act: -0.1700
Data Index: 7896924 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8467. Min Range: -5.8467
Max Act: 5.4717. Min Act: -0.1700
Data Index: 5111452 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19