Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4071 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4445. Min Range: -5.4445
Max Act: 5.4445. Min Act: -0.1700
Data Index: 2181081 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4445. Min Range: -5.4445
Max Act: 5.3820. Min Act: -0.1700
Data Index: 8645294 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4445. Min Range: -5.4445
Max Act: 5.2257. Min Act: -0.1700
Data Index: 4728430 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4445. Min Range: -5.4445
Max Act: 5.1632. Min Act: -0.1700
Data Index: 2447978 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4445. Min Range: -5.4445
Max Act: 5.1945. Min Act: -0.1700
Data Index: 2846931 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4445. Min Range: -5.4445
Max Act: 5.1007. Min Act: -0.1700
Data Index: 7574734 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4445. Min Range: -5.4445
Max Act: 5.1007. Min Act: -0.1700
Data Index: 7229003 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4445. Min Range: -5.4445
Max Act: 5.0695. Min Act: -0.1700
Data Index: 4164280 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4445. Min Range: -5.4445
Max Act: 5.0382. Min Act: -0.1700
Data Index: 502265 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4445. Min Range: -5.4445
Max Act: 4.9757. Min Act: -0.1700
Data Index: 4908286 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4445. Min Range: -5.4445
Max Act: 4.9757. Min Act: -0.1700
Data Index: 2253663 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4445. Min Range: -5.4445
Max Act: 5.0070. Min Act: -0.1700
Data Index: 8124205 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4445. Min Range: -5.4445
Max Act: 4.9445. Min Act: -0.1700
Data Index: 4272392 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4445. Min Range: -5.4445
Max Act: 4.9132. Min Act: -0.1700
Data Index: 3198234 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4445. Min Range: -5.4445
Max Act: 4.9445. Min Act: -0.1700
Data Index: 2832252 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4445. Min Range: -5.4445
Max Act: 4.9445. Min Act: -0.1700
Data Index: 7307750 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4445. Min Range: -5.4445
Max Act: 4.9445. Min Act: -0.1700
Data Index: 1470558 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4445. Min Range: -5.4445
Max Act: 4.9757. Min Act: -0.1700
Data Index: 6493164 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4445. Min Range: -5.4445
Max Act: 4.9132. Min Act: -0.1700
Data Index: 6791587 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4445. Min Range: -5.4445
Max Act: 4.9132. Min Act: -0.1700
Data Index: 5790567 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19