Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3888 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.5439. Min Act: -0.1700
Data Index: 911701 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.5127. Min Act: -0.1700
Data Index: 926238 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.4814. Min Act: -0.1700
Data Index: 8668889 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.4502. Min Act: -0.1700
Data Index: 5023244 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.4502. Min Act: -0.1700
Data Index: 2593348 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.4189. Min Act: -0.1700
Data Index: 6286364 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.4189. Min Act: -0.1700
Data Index: 4003430 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.4502. Min Act: -0.1700
Data Index: 5043785 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.4814. Min Act: -0.1700
Data Index: 1353603 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.4502. Min Act: -0.1700
Data Index: 2116369 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.4189. Min Act: -0.1700
Data Index: 4485183 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.4502. Min Act: -0.1700
Data Index: 6436973 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.3564. Min Act: -0.1700
Data Index: 1658538 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.3877. Min Act: -0.1700
Data Index: 6132697 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.3877. Min Act: -0.1700
Data Index: 7842235 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.3877. Min Act: -0.1700
Data Index: 6900861 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.3877. Min Act: -0.1700
Data Index: 1607126 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.3564. Min Act: -0.1700
Data Index: 2388632 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.3564. Min Act: -0.1700
Data Index: 4717206 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5439. Min Range: -4.5439
Max Act: 4.3564. Min Act: -0.1700
Data Index: 5627637 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19