Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2367 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.8582. Min Act: -0.1700
Data Index: 8240065 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.7957. Min Act: -0.1700
Data Index: 3325782 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.5457. Min Act: -0.1700
Data Index: 6999163 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.4519. Min Act: -0.1700
Data Index: 5451658 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.3582. Min Act: -0.1700
Data Index: 1181943 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.2957. Min Act: -0.1700
Data Index: 8468391 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.3582. Min Act: -0.1700
Data Index: 5863299 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.2957. Min Act: -0.1700
Data Index: 505036 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.2332. Min Act: -0.1700
Data Index: 7506089 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.2019. Min Act: -0.1700
Data Index: 6700729 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.1707. Min Act: -0.1700
Data Index: 4396883 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.1082. Min Act: -0.1700
Data Index: 5638712 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.1394. Min Act: -0.1700
Data Index: 3087254 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.1082. Min Act: -0.1700
Data Index: 1749407 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.0769. Min Act: -0.1700
Data Index: 3421470 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.0769. Min Act: -0.1700
Data Index: 1465975 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.0457. Min Act: -0.1700
Data Index: 5715863 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.0457. Min Act: -0.1700
Data Index: 1780207 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.0457. Min Act: -0.1700
Data Index: 5625481 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8582. Min Range: -7.8582
Max Act: 7.0144. Min Act: -0.1700
Data Index: 7062755 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19