Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3587 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1282. Min Range: -10.1282
Max Act: 10.1282. Min Act: -0.1700
Data Index: 3619678 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1282. Min Range: -10.1282
Max Act: 10.0657. Min Act: -0.1700
Data Index: 5658052 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1282. Min Range: -10.1282
Max Act: 9.9407. Min Act: -0.1700
Data Index: 2607217 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1282. Min Range: -10.1282
Max Act: 9.8782. Min Act: -0.1700
Data Index: 2129767 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1282. Min Range: -10.1282
Max Act: 9.8157. Min Act: -0.1700
Data Index: 8420656 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1282. Min Range: -10.1282
Max Act: 9.8157. Min Act: -0.1700
Data Index: 6190142 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1282. Min Range: -10.1282
Max Act: 9.8157. Min Act: -0.1700
Data Index: 138872 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1282. Min Range: -10.1282
Max Act: 9.7532. Min Act: -0.1700
Data Index: 7605826 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1282. Min Range: -10.1282
Max Act: 9.8157. Min Act: -0.1700
Data Index: 7203896 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1282. Min Range: -10.1282
Max Act: 9.7532. Min Act: -0.1700
Data Index: 6523347 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1282. Min Range: -10.1282
Max Act: 9.6907. Min Act: -0.1700
Data Index: 3610499 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1282. Min Range: -10.1282
Max Act: 9.6907. Min Act: -0.1700
Data Index: 1255571 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1282. Min Range: -10.1282
Max Act: 9.6907. Min Act: -0.1700
Data Index: 2536723 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1282. Min Range: -10.1282
Max Act: 9.6907. Min Act: -0.1700
Data Index: 8808608 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1282. Min Range: -10.1282
Max Act: 9.6907. Min Act: -0.1700
Data Index: 3923055 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1282. Min Range: -10.1282
Max Act: 9.6282. Min Act: -0.1700
Data Index: 6332650 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1282. Min Range: -10.1282
Max Act: 9.6907. Min Act: -0.1700
Data Index: 2168538 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1282. Min Range: -10.1282
Max Act: 9.6907. Min Act: -0.1700
Data Index: 1536514 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1282. Min Range: -10.1282
Max Act: 9.6282. Min Act: -0.1700
Data Index: 5539134 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1282. Min Range: -10.1282
Max Act: 9.6282. Min Act: -0.1700
Data Index: 1785833 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19