Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3339 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.8282. Min Act: -0.1700
Data Index: 2351743 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.7970. Min Act: -0.1700
Data Index: 7861049 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.7657. Min Act: -0.1700
Data Index: 1242598 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.7345. Min Act: -0.1700
Data Index: 6112643 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.5782. Min Act: -0.1700
Data Index: 4018263 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.5782. Min Act: -0.1700
Data Index: 7186746 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.5470. Min Act: -0.1700
Data Index: 4160261 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.4532. Min Act: -0.1700
Data Index: 5937649 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.4220. Min Act: -0.1700
Data Index: 5763997 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.4220. Min Act: -0.1700
Data Index: 503992 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.3907. Min Act: -0.1700
Data Index: 1414850 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.3282. Min Act: -0.1700
Data Index: 953614 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.3282. Min Act: -0.1700
Data Index: 7928332 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.3282. Min Act: -0.1700
Data Index: 6682482 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.2970. Min Act: -0.1700
Data Index: 4724414 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.2657. Min Act: -0.1700
Data Index: 5525671 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.2657. Min Act: -0.1700
Data Index: 4264530 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.2345. Min Act: -0.1700
Data Index: 3282488 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.2345. Min Act: -0.1700
Data Index: 1038777 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8282. Min Range: -6.8282
Max Act: 6.1720. Min Act: -0.1700
Data Index: 6407117 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19