Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4678 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2314. Min Range: -8.2314
Max Act: 8.2314. Min Act: -0.1700
Data Index: 1612827 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2314. Min Range: -8.2314
Max Act: 8.1689. Min Act: -0.1700
Data Index: 1328873 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2314. Min Range: -8.2314
Max Act: 8.0439. Min Act: -0.1700
Data Index: 1734758 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2314. Min Range: -8.2314
Max Act: 8.0439. Min Act: -0.1700
Data Index: 6802602 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2314. Min Range: -8.2314
Max Act: 7.9501. Min Act: -0.1700
Data Index: 7470118 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2314. Min Range: -8.2314
Max Act: 7.8876. Min Act: -0.1700
Data Index: 2707691 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2314. Min Range: -8.2314
Max Act: 7.8876. Min Act: -0.1700
Data Index: 3496418 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2314. Min Range: -8.2314
Max Act: 7.8251. Min Act: -0.1700
Data Index: 8647300 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2314. Min Range: -8.2314
Max Act: 7.8564. Min Act: -0.1700
Data Index: 2707689 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2314. Min Range: -8.2314
Max Act: 7.8564. Min Act: -0.1700
Data Index: 6602572 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2314. Min Range: -8.2314
Max Act: 7.8251. Min Act: -0.1700
Data Index: 3485585 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2314. Min Range: -8.2314
Max Act: 7.8251. Min Act: -0.1700
Data Index: 7863100 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2314. Min Range: -8.2314
Max Act: 7.8251. Min Act: -0.1700
Data Index: 1734760 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2314. Min Range: -8.2314
Max Act: 7.7939. Min Act: -0.1700
Data Index: 835701 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2314. Min Range: -8.2314
Max Act: 7.7314. Min Act: -0.1700
Data Index: 2615477 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2314. Min Range: -8.2314
Max Act: 7.7001. Min Act: -0.1700
Data Index: 644648 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2314. Min Range: -8.2314
Max Act: 7.7001. Min Act: -0.1700
Data Index: 5229608 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2314. Min Range: -8.2314
Max Act: 7.7001. Min Act: -0.1700
Data Index: 4123198 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2314. Min Range: -8.2314
Max Act: 7.7001. Min Act: -0.1700
Data Index: 5642263 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2314. Min Range: -8.2314
Max Act: 7.7001. Min Act: -0.1700
Data Index: 2014829 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19