Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 561 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7084. Min Range: -9.7084
Max Act: 9.7084. Min Act: -0.1700
Data Index: 2639019 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7084. Min Range: -9.7084
Max Act: 9.4584. Min Act: -0.1700
Data Index: 3314277 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7084. Min Range: -9.7084
Max Act: 9.3334. Min Act: -0.1700
Data Index: 6618968 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7084. Min Range: -9.7084
Max Act: 9.3334. Min Act: -0.1700
Data Index: 2209192 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7084. Min Range: -9.7084
Max Act: 9.2709. Min Act: -0.1700
Data Index: 2384155 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7084. Min Range: -9.7084
Max Act: 9.2084. Min Act: -0.1700
Data Index: 4162875 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7084. Min Range: -9.7084
Max Act: 9.2084. Min Act: -0.1700
Data Index: 1282109 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7084. Min Range: -9.7084
Max Act: 9.1459. Min Act: -0.1700
Data Index: 458454 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7084. Min Range: -9.7084
Max Act: 9.1459. Min Act: -0.1700
Data Index: 6067866 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7084. Min Range: -9.7084
Max Act: 9.2084. Min Act: -0.1700
Data Index: 2768516 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7084. Min Range: -9.7084
Max Act: 9.0209. Min Act: -0.1700
Data Index: 8485317 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7084. Min Range: -9.7084
Max Act: 8.9584. Min Act: -0.1700
Data Index: 2255260 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7084. Min Range: -9.7084
Max Act: 9.0209. Min Act: -0.1700
Data Index: 7046360 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7084. Min Range: -9.7084
Max Act: 8.8959. Min Act: -0.1700
Data Index: 723048 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7084. Min Range: -9.7084
Max Act: 8.8959. Min Act: -0.1700
Data Index: 3968559 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7084. Min Range: -9.7084
Max Act: 8.8959. Min Act: -0.1700
Data Index: 4357045 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7084. Min Range: -9.7084
Max Act: 8.8959. Min Act: -0.1700
Data Index: 1806010 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7084. Min Range: -9.7084
Max Act: 8.8959. Min Act: -0.1700
Data Index: 8363293 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7084. Min Range: -9.7084
Max Act: 8.8959. Min Act: -0.1700
Data Index: 739180 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7084. Min Range: -9.7084
Max Act: 8.8334. Min Act: -0.1700
Data Index: 5346333 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19