Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4233 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4334. Min Range: -8.4334
Max Act: 8.4334. Min Act: -0.1700
Data Index: 6252175 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4334. Min Range: -8.4334
Max Act: 8.3709. Min Act: -0.1700
Data Index: 4191200 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4334. Min Range: -8.4334
Max Act: 8.2459. Min Act: -0.1700
Data Index: 1450895 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4334. Min Range: -8.4334
Max Act: 8.2459. Min Act: -0.1700
Data Index: 3783570 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4334. Min Range: -8.4334
Max Act: 8.2459. Min Act: -0.1700
Data Index: 1193014 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4334. Min Range: -8.4334
Max Act: 8.1834. Min Act: -0.1700
Data Index: 8216854 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4334. Min Range: -8.4334
Max Act: 8.1209. Min Act: -0.1700
Data Index: 1184848 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4334. Min Range: -8.4334
Max Act: 8.0584. Min Act: -0.1700
Data Index: 3412666 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4334. Min Range: -8.4334
Max Act: 7.9959. Min Act: -0.1700
Data Index: 4592857 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4334. Min Range: -8.4334
Max Act: 7.9959. Min Act: -0.1700
Data Index: 3095454 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4334. Min Range: -8.4334
Max Act: 7.9959. Min Act: -0.1700
Data Index: 6322293 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4334. Min Range: -8.4334
Max Act: 7.9959. Min Act: -0.1700
Data Index: 3609593 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4334. Min Range: -8.4334
Max Act: 7.9959. Min Act: -0.1700
Data Index: 953257 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4334. Min Range: -8.4334
Max Act: 7.9334. Min Act: -0.1700
Data Index: 8256775 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4334. Min Range: -8.4334
Max Act: 7.9334. Min Act: -0.1700
Data Index: 5702868 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4334. Min Range: -8.4334
Max Act: 7.9334. Min Act: -0.1700
Data Index: 8643592 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4334. Min Range: -8.4334
Max Act: 7.9334. Min Act: -0.1700
Data Index: 504512 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4334. Min Range: -8.4334
Max Act: 7.9334. Min Act: -0.1700
Data Index: 4101894 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4334. Min Range: -8.4334
Max Act: 7.8709. Min Act: -0.1700
Data Index: 2188969 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4334. Min Range: -8.4334
Max Act: 7.8709. Min Act: -0.1700
Data Index: 6430887 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19