Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5065 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.7481. Min Act: -0.1700
Data Index: 2677362 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.6386. Min Act: -0.1700
Data Index: 5266757 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.5917. Min Act: -0.1700
Data Index: 8117549 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.5917. Min Act: -0.1700
Data Index: 2865196 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.5604. Min Act: -0.1700
Data Index: 7600549 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.5291. Min Act: -0.1700
Data Index: 372731 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.4977. Min Act: -0.1700
Data Index: 1975995 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.4977. Min Act: -0.1700
Data Index: 4390314 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.4821. Min Act: -0.1700
Data Index: 79736 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.4507. Min Act: -0.1700
Data Index: 3490932 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.4664. Min Act: -0.1700
Data Index: 4363639 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.4664. Min Act: -0.1700
Data Index: 3628134 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.4664. Min Act: -0.1700
Data Index: 5175677 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.4351. Min Act: -0.1700
Data Index: 1013112 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.4507. Min Act: -0.1700
Data Index: 5513205 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.4507. Min Act: -0.1700
Data Index: 795530 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.4507. Min Act: -0.1700
Data Index: 5465005 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.4351. Min Act: -0.1700
Data Index: 4540985 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.4507. Min Act: -0.1700
Data Index: 4646676 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7481. Min Range: -3.7481
Max Act: 3.4351. Min Act: -0.1700
Data Index: 5407962 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19