Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3780 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0102. Min Range: -5.0102
Max Act: 5.0102. Min Act: -0.1700
Data Index: 5378874 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0102. Min Range: -5.0102
Max Act: 5.0102. Min Act: -0.1700
Data Index: 4847822 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0102. Min Range: -5.0102
Max Act: 4.8852. Min Act: -0.1700
Data Index: 8755835 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0102. Min Range: -5.0102
Max Act: 4.8540. Min Act: -0.1700
Data Index: 6467152 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0102. Min Range: -5.0102
Max Act: 4.8540. Min Act: -0.1700
Data Index: 6114076 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0102. Min Range: -5.0102
Max Act: 4.8227. Min Act: -0.1700
Data Index: 4726861 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0102. Min Range: -5.0102
Max Act: 4.8227. Min Act: -0.1700
Data Index: 1521649 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0102. Min Range: -5.0102
Max Act: 4.7290. Min Act: -0.1700
Data Index: 2414689 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0102. Min Range: -5.0102
Max Act: 4.7290. Min Act: -0.1700
Data Index: 6310285 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0102. Min Range: -5.0102
Max Act: 4.6977. Min Act: -0.1700
Data Index: 8235089 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0102. Min Range: -5.0102
Max Act: 4.6977. Min Act: -0.1700
Data Index: 1743292 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0102. Min Range: -5.0102
Max Act: 4.6665. Min Act: -0.1700
Data Index: 8594602 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0102. Min Range: -5.0102
Max Act: 4.6352. Min Act: -0.1699
Data Index: 5928297 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0102. Min Range: -5.0102
Max Act: 4.6352. Min Act: -0.1700
Data Index: 2288647 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0102. Min Range: -5.0102
Max Act: 4.5727. Min Act: -0.1700
Data Index: 4974720 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0102. Min Range: -5.0102
Max Act: 4.6040. Min Act: -0.1700
Data Index: 2858734 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0102. Min Range: -5.0102
Max Act: 4.6040. Min Act: -0.1700
Data Index: 7271284 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0102. Min Range: -5.0102
Max Act: 4.6040. Min Act: -0.1700
Data Index: 1376024 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0102. Min Range: -5.0102
Max Act: 4.6040. Min Act: -0.1700
Data Index: 3523257 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0102. Min Range: -5.0102
Max Act: 4.5727. Min Act: -0.1700
Data Index: 4584724 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19