Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3522 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.4469. Min Act: -0.1700
Data Index: 4194505 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.4469. Min Act: -0.1700
Data Index: 855599 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.4156. Min Act: -0.1700
Data Index: 6514829 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.3844. Min Act: -0.1700
Data Index: 1746108 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.3844. Min Act: -0.1700
Data Index: 5947413 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.3219. Min Act: -0.1700
Data Index: 3781982 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.2906. Min Act: -0.1700
Data Index: 1507502 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.2594. Min Act: -0.1700
Data Index: 825394 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.2594. Min Act: -0.1700
Data Index: 855598 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.1968. Min Act: -0.1700
Data Index: 1546193 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.2281. Min Act: -0.1700
Data Index: 4794008 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.2281. Min Act: -0.1700
Data Index: 6053362 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.1968. Min Act: -0.1700
Data Index: 4675578 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.1968. Min Act: -0.1700
Data Index: 7550894 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.1656. Min Act: -0.1700
Data Index: 4213113 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.1343. Min Act: -0.1700
Data Index: 5316858 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.1656. Min Act: -0.1700
Data Index: 2864317 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.1656. Min Act: -0.1700
Data Index: 3464901 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.1343. Min Act: -0.1700
Data Index: 2865964 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4469. Min Range: -4.4469
Max Act: 4.1968. Min Act: -0.1700
Data Index: 2550359 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19