Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1388 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6216. Min Range: -8.6216
Max Act: 8.6216. Min Act: -0.1700
Data Index: 753173 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6216. Min Range: -8.6216
Max Act: 8.4341. Min Act: -0.1700
Data Index: 1624124 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6216. Min Range: -8.6216
Max Act: 8.3716. Min Act: -0.1700
Data Index: 1241367 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6216. Min Range: -8.6216
Max Act: 8.2778. Min Act: -0.1700
Data Index: 1241374 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6216. Min Range: -8.6216
Max Act: 8.2153. Min Act: -0.1700
Data Index: 4176273 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6216. Min Range: -8.6216
Max Act: 8.1841. Min Act: -0.1700
Data Index: 4194108 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6216. Min Range: -8.6216
Max Act: 8.2466. Min Act: -0.1700
Data Index: 2725164 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6216. Min Range: -8.6216
Max Act: 8.1841. Min Act: -0.1700
Data Index: 3982971 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6216. Min Range: -8.6216
Max Act: 8.1528. Min Act: -0.1700
Data Index: 148625 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6216. Min Range: -8.6216
Max Act: 8.1216. Min Act: -0.1700
Data Index: 6387569 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6216. Min Range: -8.6216
Max Act: 8.1216. Min Act: -0.1700
Data Index: 6550695 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6216. Min Range: -8.6216
Max Act: 8.1216. Min Act: -0.1700
Data Index: 5926643 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6216. Min Range: -8.6216
Max Act: 8.0591. Min Act: -0.1700
Data Index: 1567374 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6216. Min Range: -8.6216
Max Act: 8.0591. Min Act: -0.1700
Data Index: 4023285 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6216. Min Range: -8.6216
Max Act: 8.0278. Min Act: -0.1700
Data Index: 8159073 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6216. Min Range: -8.6216
Max Act: 8.0278. Min Act: -0.1700
Data Index: 4829582 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6216. Min Range: -8.6216
Max Act: 7.9966. Min Act: -0.1700
Data Index: 1308614 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6216. Min Range: -8.6216
Max Act: 7.9966. Min Act: -0.1700
Data Index: 692267 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6216. Min Range: -8.6216
Max Act: 7.9653. Min Act: -0.1700
Data Index: 4529230 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6216. Min Range: -8.6216
Max Act: 7.9653. Min Act: -0.1700
Data Index: 6160377 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19