Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3027 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4007. Min Range: -7.4007
Max Act: 7.4007. Min Act: -0.1700
Data Index: 6492009 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4007. Min Range: -7.4007
Max Act: 6.9632. Min Act: -0.1700
Data Index: 7785338 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4007. Min Range: -7.4007
Max Act: 6.9632. Min Act: -0.1700
Data Index: 6944332 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4007. Min Range: -7.4007
Max Act: 6.9007. Min Act: -0.1700
Data Index: 2193191 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4007. Min Range: -7.4007
Max Act: 6.8695. Min Act: -0.1700
Data Index: 3648369 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4007. Min Range: -7.4007
Max Act: 6.9007. Min Act: -0.1700
Data Index: 3846131 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4007. Min Range: -7.4007
Max Act: 6.8382. Min Act: -0.1700
Data Index: 150556 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4007. Min Range: -7.4007
Max Act: 6.8382. Min Act: -0.1700
Data Index: 3523034 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4007. Min Range: -7.4007
Max Act: 6.8070. Min Act: -0.1700
Data Index: 3847699 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4007. Min Range: -7.4007
Max Act: 6.8070. Min Act: -0.1700
Data Index: 3456323 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4007. Min Range: -7.4007
Max Act: 6.8070. Min Act: -0.1700
Data Index: 5515000 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4007. Min Range: -7.4007
Max Act: 6.7445. Min Act: -0.1700
Data Index: 3657684 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4007. Min Range: -7.4007
Max Act: 6.7445. Min Act: -0.1700
Data Index: 6687740 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4007. Min Range: -7.4007
Max Act: 6.7757. Min Act: -0.1700
Data Index: 2584614 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4007. Min Range: -7.4007
Max Act: 6.7132. Min Act: -0.1700
Data Index: 5274343 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4007. Min Range: -7.4007
Max Act: 6.7132. Min Act: -0.1700
Data Index: 4311510 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4007. Min Range: -7.4007
Max Act: 6.7132. Min Act: -0.1700
Data Index: 4844752 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4007. Min Range: -7.4007
Max Act: 6.7132. Min Act: -0.1700
Data Index: 1443935 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4007. Min Range: -7.4007
Max Act: 6.6820. Min Act: -0.1700
Data Index: 908383 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4007. Min Range: -7.4007
Max Act: 6.6820. Min Act: -0.1700
Data Index: 8455348 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19