Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3500 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0339. Min Range: -10.0339
Max Act: 10.0339. Min Act: -0.1700
Data Index: 7692856 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0339. Min Range: -10.0339
Max Act: 9.7839. Min Act: -0.1700
Data Index: 7251519 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0339. Min Range: -10.0339
Max Act: 9.6589. Min Act: -0.1700
Data Index: 8317568 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0339. Min Range: -10.0339
Max Act: 9.5964. Min Act: -0.1700
Data Index: 8454626 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0339. Min Range: -10.0339
Max Act: 9.4714. Min Act: -0.1700
Data Index: 356627 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0339. Min Range: -10.0339
Max Act: 9.4089. Min Act: -0.1700
Data Index: 8007812 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0339. Min Range: -10.0339
Max Act: 9.4089. Min Act: -0.1700
Data Index: 549689 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0339. Min Range: -10.0339
Max Act: 9.3464. Min Act: -0.1700
Data Index: 6268596 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0339. Min Range: -10.0339
Max Act: 9.3464. Min Act: -0.1700
Data Index: 6138332 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0339. Min Range: -10.0339
Max Act: 9.3464. Min Act: -0.1700
Data Index: 6240759 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0339. Min Range: -10.0339
Max Act: 9.2214. Min Act: -0.1700
Data Index: 1160673 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0339. Min Range: -10.0339
Max Act: 9.1589. Min Act: -0.1700
Data Index: 5170410 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0339. Min Range: -10.0339
Max Act: 9.1589. Min Act: -0.1700
Data Index: 821515 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0339. Min Range: -10.0339
Max Act: 9.1589. Min Act: -0.1700
Data Index: 8800057 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0339. Min Range: -10.0339
Max Act: 9.0964. Min Act: -0.1700
Data Index: 5003659 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0339. Min Range: -10.0339
Max Act: 9.0964. Min Act: -0.1700
Data Index: 903612 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0339. Min Range: -10.0339
Max Act: 9.0339. Min Act: -0.1700
Data Index: 3018201 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0339. Min Range: -10.0339
Max Act: 9.0964. Min Act: -0.1700
Data Index: 2065959 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0339. Min Range: -10.0339
Max Act: 9.0964. Min Act: -0.1700
Data Index: 5032551 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0339. Min Range: -10.0339
Max Act: 9.0964. Min Act: -0.1700
Data Index: 7813267 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19