Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3927 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.4661. Min Act: -0.1700
Data Index: 147961 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.3723. Min Act: -0.1700
Data Index: 6248977 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.3723. Min Act: -0.1700
Data Index: 5381370 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.3723. Min Act: -0.1700
Data Index: 680399 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.2786. Min Act: -0.1700
Data Index: 7788755 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.2473. Min Act: -0.1700
Data Index: 7332649 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.2786. Min Act: -0.1700
Data Index: 5397085 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.2161. Min Act: -0.1700
Data Index: 3110007 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.1848. Min Act: -0.1700
Data Index: 8523011 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.1848. Min Act: -0.1700
Data Index: 3022874 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.1536. Min Act: -0.1700
Data Index: 2005612 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.1536. Min Act: -0.1700
Data Index: 3595493 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.1223. Min Act: -0.1700
Data Index: 3362198 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.1536. Min Act: -0.1700
Data Index: 206347 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.1536. Min Act: -0.1700
Data Index: 5207572 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.1536. Min Act: -0.1700
Data Index: 3873013 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.1536. Min Act: -0.1700
Data Index: 8511864 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.1223. Min Act: -0.1700
Data Index: 1813370 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.1223. Min Act: -0.1700
Data Index: 2560899 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4661. Min Range: -5.4661
Max Act: 5.1223. Min Act: -0.1700
Data Index: 4283130 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19