Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2022 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.4344. Min Act: -0.1700
Data Index: 6511389 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.3719. Min Act: -0.1700
Data Index: 6279078 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.2781. Min Act: -0.1700
Data Index: 7448523 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.2781. Min Act: -0.1700
Data Index: 2533658 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.2781. Min Act: -0.1700
Data Index: 2282383 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.2156. Min Act: -0.1700
Data Index: 6069644 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.2156. Min Act: -0.1700
Data Index: 3932948 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.2156. Min Act: -0.1700
Data Index: 4546147 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.1844. Min Act: -0.1700
Data Index: 7080777 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.1844. Min Act: -0.1700
Data Index: 1166250 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.1844. Min Act: -0.1700
Data Index: 7835950 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.2156. Min Act: -0.1700
Data Index: 1832160 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.1844. Min Act: -0.1700
Data Index: 4396469 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.1531. Min Act: -0.1700
Data Index: 6830802 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.1531. Min Act: -0.1700
Data Index: 7925441 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.1531. Min Act: -0.1700
Data Index: 610167 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.1219. Min Act: -0.1700
Data Index: 3572182 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.1531. Min Act: -0.1700
Data Index: 4631263 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.1531. Min Act: -0.1700
Data Index: 4655105 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4344. Min Range: -6.4344
Max Act: 6.1531. Min Act: -0.1700
Data Index: 3572335 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19