Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4084 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.8145. Min Act: -0.1700
Data Index: 7947810 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.4395. Min Act: -0.1700
Data Index: 6079041 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.3770. Min Act: -0.1700
Data Index: 5852005 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.2520. Min Act: -0.1700
Data Index: 6111356 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.3145. Min Act: -0.1700
Data Index: 4488972 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.2833. Min Act: -0.1700
Data Index: 6914944 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.2520. Min Act: -0.1700
Data Index: 2760368 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.2208. Min Act: -0.1700
Data Index: 1718502 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.2208. Min Act: -0.1700
Data Index: 7450148 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.2208. Min Act: -0.1700
Data Index: 530024 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.2208. Min Act: -0.1700
Data Index: 3324911 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.1583. Min Act: -0.1700
Data Index: 7083926 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.1895. Min Act: -0.1700
Data Index: 637953 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.0958. Min Act: -0.1700
Data Index: 6440115 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.1270. Min Act: -0.1700
Data Index: 2498704 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.1583. Min Act: -0.1700
Data Index: 1361979 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.1270. Min Act: -0.1700
Data Index: 6322468 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.1270. Min Act: -0.1700
Data Index: 3211586 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.1270. Min Act: -0.1700
Data Index: 3764513 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8145. Min Range: -5.8145
Max Act: 5.0333. Min Act: -0.1700
Data Index: 6355320 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19