Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3513 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1342. Min Range: -7.1342
Max Act: 7.1342. Min Act: -0.1700
Data Index: 1293534 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1342. Min Range: -7.1342
Max Act: 6.9155. Min Act: -0.1700
Data Index: 5697927 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1342. Min Range: -7.1342
Max Act: 6.9155. Min Act: -0.1700
Data Index: 947698 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1342. Min Range: -7.1342
Max Act: 6.8530. Min Act: -0.1700
Data Index: 6451790 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1342. Min Range: -7.1342
Max Act: 6.8217. Min Act: -0.1700
Data Index: 8524611 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1342. Min Range: -7.1342
Max Act: 6.7905. Min Act: -0.1700
Data Index: 7451115 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1342. Min Range: -7.1342
Max Act: 6.7592. Min Act: -0.1700
Data Index: 3181607 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1342. Min Range: -7.1342
Max Act: 6.7280. Min Act: -0.1700
Data Index: 1317346 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1342. Min Range: -7.1342
Max Act: 6.7280. Min Act: -0.1700
Data Index: 5077429 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1342. Min Range: -7.1342
Max Act: 6.7280. Min Act: -0.1700
Data Index: 1820314 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1342. Min Range: -7.1342
Max Act: 6.6967. Min Act: -0.1700
Data Index: 6480594 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1342. Min Range: -7.1342
Max Act: 6.6967. Min Act: -0.1700
Data Index: 1514387 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1342. Min Range: -7.1342
Max Act: 6.6967. Min Act: -0.1700
Data Index: 7476624 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1342. Min Range: -7.1342
Max Act: 6.6030. Min Act: -0.1700
Data Index: 3490551 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1342. Min Range: -7.1342
Max Act: 6.6342. Min Act: -0.1700
Data Index: 422042 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1342. Min Range: -7.1342
Max Act: 6.6342. Min Act: -0.1700
Data Index: 3206304 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1342. Min Range: -7.1342
Max Act: 6.6342. Min Act: -0.1700
Data Index: 7256036 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1342. Min Range: -7.1342
Max Act: 6.5717. Min Act: -0.1700
Data Index: 3329214 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1342. Min Range: -7.1342
Max Act: 6.6030. Min Act: -0.1700
Data Index: 1460538 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1342. Min Range: -7.1342
Max Act: 6.6030. Min Act: -0.1700
Data Index: 6991228 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19