Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3023 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2018. Min Range: -7.2018
Max Act: 7.2018. Min Act: -0.1700
Data Index: 7524979 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2018. Min Range: -7.2018
Max Act: 7.1081. Min Act: -0.1700
Data Index: 8398045 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2018. Min Range: -7.2018
Max Act: 6.8893. Min Act: -0.1700
Data Index: 2084410 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2018. Min Range: -7.2018
Max Act: 6.7643. Min Act: -0.1700
Data Index: 8231652 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2018. Min Range: -7.2018
Max Act: 6.7643. Min Act: -0.1700
Data Index: 486375 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2018. Min Range: -7.2018
Max Act: 6.7331. Min Act: -0.1700
Data Index: 6470404 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2018. Min Range: -7.2018
Max Act: 6.7331. Min Act: -0.1700
Data Index: 2009461 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2018. Min Range: -7.2018
Max Act: 6.7331. Min Act: -0.1700
Data Index: 8071371 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2018. Min Range: -7.2018
Max Act: 6.5768. Min Act: -0.1700
Data Index: 3148764 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2018. Min Range: -7.2018
Max Act: 6.6081. Min Act: -0.1700
Data Index: 4094336 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2018. Min Range: -7.2018
Max Act: 6.6081. Min Act: -0.1700
Data Index: 5842775 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2018. Min Range: -7.2018
Max Act: 6.5768. Min Act: -0.1700
Data Index: 7137824 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2018. Min Range: -7.2018
Max Act: 6.5768. Min Act: -0.1700
Data Index: 3193469 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2018. Min Range: -7.2018
Max Act: 6.5768. Min Act: -0.1700
Data Index: 498636 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2018. Min Range: -7.2018
Max Act: 6.5456. Min Act: -0.1700
Data Index: 3053962 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2018. Min Range: -7.2018
Max Act: 6.4831. Min Act: -0.1700
Data Index: 4556745 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2018. Min Range: -7.2018
Max Act: 6.4518. Min Act: -0.1700
Data Index: 1373643 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2018. Min Range: -7.2018
Max Act: 6.4518. Min Act: -0.1700
Data Index: 2098392 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2018. Min Range: -7.2018
Max Act: 6.4518. Min Act: -0.1700
Data Index: 4951422 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2018. Min Range: -7.2018
Max Act: 6.4206. Min Act: -0.1700
Data Index: 4509573 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19