Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 658 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.6297. Min Act: -0.1700
Data Index: 8145687 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.5330. Min Act: -0.1700
Data Index: 3057309 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.5330. Min Act: -0.1700
Data Index: 3311250 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.5168. Min Act: -0.1700
Data Index: 547922 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.5330. Min Act: -0.1700
Data Index: 8280028 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.5168. Min Act: -0.1700
Data Index: 2868235 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.5007. Min Act: -0.1700
Data Index: 5049417 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4844. Min Act: -0.1700
Data Index: 3832513 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4682. Min Act: -0.1700
Data Index: 4732992 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4844. Min Act: -0.1700
Data Index: 7607715 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4844. Min Act: -0.1700
Data Index: 233178 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4682. Min Act: -0.1700
Data Index: 4169439 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4682. Min Act: -0.1700
Data Index: 3375859 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4682. Min Act: -0.1700
Data Index: 2178089 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4520. Min Act: -0.1700
Data Index: 3178725 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4520. Min Act: -0.1700
Data Index: 14844 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4520. Min Act: -0.1700
Data Index: 1797726 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4357. Min Act: -0.1700
Data Index: 7709324 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4357. Min Act: -0.1700
Data Index: 3178719 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4520. Min Act: -0.1700
Data Index: 3832511 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19