Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5097 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3731. Min Range: -8.3731
Max Act: 8.3731. Min Act: -0.1700
Data Index: 5843877 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3731. Min Range: -8.3731
Max Act: 8.3106. Min Act: -0.1700
Data Index: 1235494 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3731. Min Range: -8.3731
Max Act: 8.2481. Min Act: -0.1700
Data Index: 7481468 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3731. Min Range: -8.3731
Max Act: 8.2481. Min Act: -0.1700
Data Index: 8079758 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3731. Min Range: -8.3731
Max Act: 8.1856. Min Act: -0.1700
Data Index: 8689965 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3731. Min Range: -8.3731
Max Act: 8.1231. Min Act: -0.1700
Data Index: 3270605 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3731. Min Range: -8.3731
Max Act: 7.9981. Min Act: -0.1700
Data Index: 8825413 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3731. Min Range: -8.3731
Max Act: 7.9356. Min Act: -0.1700
Data Index: 2423982 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3731. Min Range: -8.3731
Max Act: 7.9356. Min Act: -0.1700
Data Index: 5271652 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3731. Min Range: -8.3731
Max Act: 7.8419. Min Act: -0.1700
Data Index: 1008880 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3731. Min Range: -8.3731
Max Act: 7.8731. Min Act: -0.1700
Data Index: 7417532 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3731. Min Range: -8.3731
Max Act: 7.8419. Min Act: -0.1700
Data Index: 6837769 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3731. Min Range: -8.3731
Max Act: 7.8106. Min Act: -0.1700
Data Index: 3153025 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3731. Min Range: -8.3731
Max Act: 7.7794. Min Act: -0.1700
Data Index: 802979 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3731. Min Range: -8.3731
Max Act: 7.7794. Min Act: -0.1700
Data Index: 5956174 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3731. Min Range: -8.3731
Max Act: 7.7481. Min Act: -0.1700
Data Index: 1396863 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3731. Min Range: -8.3731
Max Act: 7.7481. Min Act: -0.1700
Data Index: 7594720 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3731. Min Range: -8.3731
Max Act: 7.7481. Min Act: -0.1700
Data Index: 3001368 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3731. Min Range: -8.3731
Max Act: 7.7481. Min Act: -0.1700
Data Index: 7757173 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3731. Min Range: -8.3731
Max Act: 7.7481. Min Act: -0.1700
Data Index: 53812 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19