Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2824 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0219. Min Range: -8.0219
Max Act: 8.0219. Min Act: -0.1700
Data Index: 1995893 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0219. Min Range: -8.0219
Max Act: 8.0219. Min Act: -0.1700
Data Index: 5859425 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0219. Min Range: -8.0219
Max Act: 7.8969. Min Act: -0.1700
Data Index: 7150460 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0219. Min Range: -8.0219
Max Act: 7.8969. Min Act: -0.1700
Data Index: 378660 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0219. Min Range: -8.0219
Max Act: 7.8969. Min Act: -0.1700
Data Index: 617965 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0219. Min Range: -8.0219
Max Act: 7.8344. Min Act: -0.1700
Data Index: 4522248 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0219. Min Range: -8.0219
Max Act: 7.7719. Min Act: -0.1700
Data Index: 8788552 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0219. Min Range: -8.0219
Max Act: 7.7719. Min Act: -0.1700
Data Index: 2509286 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0219. Min Range: -8.0219
Max Act: 7.7719. Min Act: -0.1700
Data Index: 6389403 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0219. Min Range: -8.0219
Max Act: 7.7094. Min Act: -0.1700
Data Index: 814258 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0219. Min Range: -8.0219
Max Act: 7.7094. Min Act: -0.1700
Data Index: 532906 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0219. Min Range: -8.0219
Max Act: 7.7094. Min Act: -0.1700
Data Index: 6085364 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0219. Min Range: -8.0219
Max Act: 7.7094. Min Act: -0.1700
Data Index: 5985874 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0219. Min Range: -8.0219
Max Act: 7.6782. Min Act: -0.1700
Data Index: 8470264 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0219. Min Range: -8.0219
Max Act: 7.6157. Min Act: -0.1700
Data Index: 3915761 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0219. Min Range: -8.0219
Max Act: 7.6469. Min Act: -0.1700
Data Index: 4678428 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0219. Min Range: -8.0219
Max Act: 7.6157. Min Act: -0.1700
Data Index: 3352466 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0219. Min Range: -8.0219
Max Act: 7.5844. Min Act: -0.1700
Data Index: 2299562 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0219. Min Range: -8.0219
Max Act: 7.4907. Min Act: -0.1700
Data Index: 7352485 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0219. Min Range: -8.0219
Max Act: 7.5219. Min Act: -0.1700
Data Index: 7556097 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19