Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5414 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4468. Min Range: -7.4468
Max Act: 7.4468. Min Act: -0.1700
Data Index: 814508 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4468. Min Range: -7.4468
Max Act: 7.3843. Min Act: -0.1700
Data Index: 2851022 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4468. Min Range: -7.4468
Max Act: 7.3218. Min Act: -0.1700
Data Index: 8129220 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4468. Min Range: -7.4468
Max Act: 7.2906. Min Act: -0.1700
Data Index: 2555903 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4468. Min Range: -7.4468
Max Act: 7.2281. Min Act: -0.1700
Data Index: 5740942 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4468. Min Range: -7.4468
Max Act: 7.2593. Min Act: -0.1700
Data Index: 5650546 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4468. Min Range: -7.4468
Max Act: 7.2593. Min Act: -0.1700
Data Index: 4340271 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4468. Min Range: -7.4468
Max Act: 7.2593. Min Act: -0.1700
Data Index: 6975895 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4468. Min Range: -7.4468
Max Act: 7.2593. Min Act: -0.1700
Data Index: 3378964 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4468. Min Range: -7.4468
Max Act: 7.2281. Min Act: -0.1700
Data Index: 8773515 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4468. Min Range: -7.4468
Max Act: 7.1968. Min Act: -0.1700
Data Index: 8773514 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4468. Min Range: -7.4468
Max Act: 7.1968. Min Act: -0.1700
Data Index: 7358980 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4468. Min Range: -7.4468
Max Act: 7.1968. Min Act: -0.1700
Data Index: 5002992 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4468. Min Range: -7.4468
Max Act: 7.1343. Min Act: -0.1700
Data Index: 3125670 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4468. Min Range: -7.4468
Max Act: 7.1656. Min Act: -0.1700
Data Index: 6005415 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4468. Min Range: -7.4468
Max Act: 7.1031. Min Act: -0.1700
Data Index: 6073813 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4468. Min Range: -7.4468
Max Act: 7.0406. Min Act: -0.1700
Data Index: 3605950 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4468. Min Range: -7.4468
Max Act: 7.0406. Min Act: -0.1700
Data Index: 4231504 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4468. Min Range: -7.4468
Max Act: 7.0406. Min Act: -0.1700
Data Index: 427327 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4468. Min Range: -7.4468
Max Act: 6.9781. Min Act: -0.1700
Data Index: 4458076 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19