Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.5408. Min Act: -0.1700
Data Index: 8408654 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.4783. Min Act: -0.1700
Data Index: 747897 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.4158. Min Act: -0.1700
Data Index: 2036623 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.3845. Min Act: -0.1700
Data Index: 8639001 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.3533. Min Act: -0.1700
Data Index: 127889 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.3533. Min Act: -0.1700
Data Index: 1243024 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.2908. Min Act: -0.1700
Data Index: 321746 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.3220. Min Act: -0.1700
Data Index: 1243021 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.2908. Min Act: -0.1700
Data Index: 498709 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.2283. Min Act: -0.1700
Data Index: 27985 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.1970. Min Act: -0.1700
Data Index: 3105057 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.1970. Min Act: -0.1700
Data Index: 4363376 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.1970. Min Act: -0.1700
Data Index: 1243025 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.1658. Min Act: -0.1700
Data Index: 7620228 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.1970. Min Act: -0.1700
Data Index: 38879 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.1658. Min Act: -0.1700
Data Index: 2036620 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.1345. Min Act: -0.1700
Data Index: 747898 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.1970. Min Act: -0.1700
Data Index: 4228038 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.1345. Min Act: -0.1700
Data Index: 6569219 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5408. Min Range: -6.5408
Max Act: 6.1345. Min Act: -0.1700
Data Index: 8408660 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19