Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3334 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.8689. Min Act: -0.1700
Data Index: 2890592 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.8377. Min Act: -0.1700
Data Index: 5837189 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.7127. Min Act: -0.1700
Data Index: 356420 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.6502. Min Act: -0.1700
Data Index: 3870953 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.6502. Min Act: -0.1700
Data Index: 7778528 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.6502. Min Act: -0.1700
Data Index: 7559965 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.6189. Min Act: -0.1700
Data Index: 2598249 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.6189. Min Act: -0.1700
Data Index: 5477365 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.6189. Min Act: -0.1700
Data Index: 2468979 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.5877. Min Act: -0.1700
Data Index: 4117179 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.5877. Min Act: -0.1700
Data Index: 3167498 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.5877. Min Act: -0.1700
Data Index: 503760 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.5877. Min Act: -0.1700
Data Index: 5055393 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.5564. Min Act: -0.1700
Data Index: 1250898 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.5252. Min Act: -0.1700
Data Index: 5511512 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.5564. Min Act: -0.1700
Data Index: 4765778 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.5252. Min Act: -0.1700
Data Index: 8779723 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.5252. Min Act: -0.1700
Data Index: 614484 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.5564. Min Act: -0.1700
Data Index: 2711510 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8689. Min Range: -5.8689
Max Act: 5.5252. Min Act: -0.1700
Data Index: 8819365 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19