Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3244 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6524. Min Range: -4.6524
Max Act: 4.6524. Min Act: -0.1700
Data Index: 5680045 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6524. Min Range: -4.6524
Max Act: 4.4649. Min Act: -0.1700
Data Index: 1638256 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6524. Min Range: -4.6524
Max Act: 4.4962. Min Act: -0.1700
Data Index: 7512011 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6524. Min Range: -4.6524
Max Act: 4.3087. Min Act: -0.1700
Data Index: 3192451 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6524. Min Range: -4.6524
Max Act: 4.2462. Min Act: -0.1700
Data Index: 4852182 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6524. Min Range: -4.6524
Max Act: 4.1837. Min Act: -0.1700
Data Index: 8430522 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6524. Min Range: -4.6524
Max Act: 4.1837. Min Act: -0.1700
Data Index: 8276244 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6524. Min Range: -4.6524
Max Act: 4.1837. Min Act: -0.1700
Data Index: 6877817 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6524. Min Range: -4.6524
Max Act: 4.1212. Min Act: -0.1700
Data Index: 7326510 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6524. Min Range: -4.6524
Max Act: 4.1212. Min Act: -0.1700
Data Index: 3463958 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6524. Min Range: -4.6524
Max Act: 4.0899. Min Act: -0.1700
Data Index: 5169561 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6524. Min Range: -4.6524
Max Act: 4.0899. Min Act: -0.1700
Data Index: 3292506 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6524. Min Range: -4.6524
Max Act: 4.0586. Min Act: -0.1700
Data Index: 4272768 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6524. Min Range: -4.6524
Max Act: 4.0586. Min Act: -0.1700
Data Index: 5486124 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6524. Min Range: -4.6524
Max Act: 4.0274. Min Act: -0.1700
Data Index: 1981822 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6524. Min Range: -4.6524
Max Act: 4.0274. Min Act: -0.1700
Data Index: 8820517 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6524. Min Range: -4.6524
Max Act: 3.9961. Min Act: -0.1700
Data Index: 2003715 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6524. Min Range: -4.6524
Max Act: 3.9961. Min Act: -0.1700
Data Index: 4734361 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6524. Min Range: -4.6524
Max Act: 3.9961. Min Act: -0.1700
Data Index: 4505080 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6524. Min Range: -4.6524
Max Act: 3.9961. Min Act: -0.1700
Data Index: 4348175 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19