Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2515 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0314. Min Range: -5.0314
Max Act: 5.0314. Min Act: -0.1700
Data Index: 1608594 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0314. Min Range: -5.0314
Max Act: 5.0314. Min Act: -0.1700
Data Index: 469849 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0314. Min Range: -5.0314
Max Act: 5.0002. Min Act: -0.1700
Data Index: 5703719 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0314. Min Range: -5.0314
Max Act: 4.9064. Min Act: -0.1700
Data Index: 5561741 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0314. Min Range: -5.0314
Max Act: 4.8752. Min Act: -0.1700
Data Index: 6026474 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0314. Min Range: -5.0314
Max Act: 4.8439. Min Act: -0.1700
Data Index: 2444727 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0314. Min Range: -5.0314
Max Act: 4.7814. Min Act: -0.1700
Data Index: 2030804 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0314. Min Range: -5.0314
Max Act: 4.7814. Min Act: -0.1700
Data Index: 5688944 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0314. Min Range: -5.0314
Max Act: 4.8127. Min Act: -0.1700
Data Index: 617349 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0314. Min Range: -5.0314
Max Act: 4.7814. Min Act: -0.1700
Data Index: 269532 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0314. Min Range: -5.0314
Max Act: 4.7814. Min Act: -0.1700
Data Index: 3257444 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0314. Min Range: -5.0314
Max Act: 4.7814. Min Act: -0.1700
Data Index: 8462111 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0314. Min Range: -5.0314
Max Act: 4.7814. Min Act: -0.1700
Data Index: 5411623 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0314. Min Range: -5.0314
Max Act: 4.8127. Min Act: -0.1700
Data Index: 7909966 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0314. Min Range: -5.0314
Max Act: 4.7502. Min Act: -0.1700
Data Index: 7137414 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0314. Min Range: -5.0314
Max Act: 4.7502. Min Act: -0.1700
Data Index: 6256012 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0314. Min Range: -5.0314
Max Act: 4.7502. Min Act: -0.1700
Data Index: 7340075 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0314. Min Range: -5.0314
Max Act: 4.7189. Min Act: -0.1700
Data Index: 4291555 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0314. Min Range: -5.0314
Max Act: 4.7189. Min Act: -0.1700
Data Index: 3764873 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0314. Min Range: -5.0314
Max Act: 4.7189. Min Act: -0.1700
Data Index: 3185020 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19