Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5404 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2608. Min Range: -7.2608
Max Act: 7.2608. Min Act: -0.1700
Data Index: 4815000 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2608. Min Range: -7.2608
Max Act: 7.1358. Min Act: -0.1700
Data Index: 1707319 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2608. Min Range: -7.2608
Max Act: 7.1358. Min Act: -0.1700
Data Index: 5756915 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2608. Min Range: -7.2608
Max Act: 7.0108. Min Act: -0.1700
Data Index: 6925151 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2608. Min Range: -7.2608
Max Act: 6.9483. Min Act: -0.1700
Data Index: 1386446 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2608. Min Range: -7.2608
Max Act: 6.7296. Min Act: -0.1700
Data Index: 4022257 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2608. Min Range: -7.2608
Max Act: 6.7296. Min Act: -0.1700
Data Index: 1063659 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2608. Min Range: -7.2608
Max Act: 6.7296. Min Act: -0.1700
Data Index: 1403181 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2608. Min Range: -7.2608
Max Act: 6.7296. Min Act: -0.1700
Data Index: 5285093 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2608. Min Range: -7.2608
Max Act: 6.6983. Min Act: -0.1700
Data Index: 6615394 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2608. Min Range: -7.2608
Max Act: 6.6358. Min Act: -0.1700
Data Index: 5292735 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2608. Min Range: -7.2608
Max Act: 6.6358. Min Act: -0.1700
Data Index: 5736617 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2608. Min Range: -7.2608
Max Act: 6.6358. Min Act: -0.1700
Data Index: 1848471 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2608. Min Range: -7.2608
Max Act: 6.6046. Min Act: -0.1700
Data Index: 7014638 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2608. Min Range: -7.2608
Max Act: 6.5733. Min Act: -0.1700
Data Index: 3149536 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2608. Min Range: -7.2608
Max Act: 6.5421. Min Act: -0.1700
Data Index: 367897 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2608. Min Range: -7.2608
Max Act: 6.5108. Min Act: -0.1700
Data Index: 8408393 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2608. Min Range: -7.2608
Max Act: 6.4796. Min Act: -0.1700
Data Index: 8303801 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2608. Min Range: -7.2608
Max Act: 6.4796. Min Act: -0.1700
Data Index: 1806573 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2608. Min Range: -7.2608
Max Act: 6.4796. Min Act: -0.1700
Data Index: 2969715 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19