Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.5708. Min Act: -0.1700
Data Index: 407807 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.5395. Min Act: -0.1700
Data Index: 8820178 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.4770. Min Act: -0.1700
Data Index: 4389772 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.4458. Min Act: -0.1700
Data Index: 7402314 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.3833. Min Act: -0.1700
Data Index: 409658 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.3520. Min Act: -0.1700
Data Index: 1238134 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.3520. Min Act: -0.1700
Data Index: 6958428 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.2895. Min Act: -0.1700
Data Index: 1760297 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.3208. Min Act: -0.1700
Data Index: 3267305 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.3208. Min Act: -0.1700
Data Index: 2492614 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.3208. Min Act: -0.1700
Data Index: 2771058 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.2895. Min Act: -0.1700
Data Index: 972891 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.2583. Min Act: -0.1700
Data Index: 5259120 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.2583. Min Act: -0.1700
Data Index: 3682851 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.2583. Min Act: -0.1700
Data Index: 252094 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.2583. Min Act: -0.1700
Data Index: 3661638 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.2270. Min Act: -0.1700
Data Index: 2828834 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.2270. Min Act: -0.1700
Data Index: 8832842 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.2270. Min Act: -0.1700
Data Index: 6137073 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5708. Min Range: -4.5708
Max Act: 4.1645. Min Act: -0.1700
Data Index: 1366391 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19