Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3034 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.8380. Min Act: -0.1700
Data Index: 8462975 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.6818. Min Act: -0.1700
Data Index: 1683988 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.5568. Min Act: -0.1700
Data Index: 360855 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.5880. Min Act: -0.1700
Data Index: 6116868 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.5255. Min Act: -0.1700
Data Index: 5358554 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.4005. Min Act: -0.1700
Data Index: 7052418 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.3380. Min Act: -0.1700
Data Index: 1946323 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.3068. Min Act: -0.1700
Data Index: 6943633 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.2755. Min Act: -0.1700
Data Index: 832648 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.2755. Min Act: -0.1700
Data Index: 4247583 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.2755. Min Act: -0.1700
Data Index: 4054390 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.2443. Min Act: -0.1700
Data Index: 1521118 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.2443. Min Act: -0.1700
Data Index: 3847469 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.2130. Min Act: -0.1700
Data Index: 6832523 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.2130. Min Act: -0.1700
Data Index: 2884792 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.1818. Min Act: -0.1700
Data Index: 4712569 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.2130. Min Act: -0.1700
Data Index: 7145884 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.1505. Min Act: -0.1700
Data Index: 6522777 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.1818. Min Act: -0.1700
Data Index: 1899995 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8380. Min Range: -4.8380
Max Act: 4.1818. Min Act: -0.1700
Data Index: 5380536 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19