Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 307 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6818. Min Range: -5.6818
Max Act: 5.6818. Min Act: -0.1700
Data Index: 4901752 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6818. Min Range: -5.6818
Max Act: 5.3068. Min Act: -0.1700
Data Index: 8589679 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6818. Min Range: -5.6818
Max Act: 5.0880. Min Act: -0.1700
Data Index: 931149 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6818. Min Range: -5.6818
Max Act: 4.9005. Min Act: -0.1700
Data Index: 5158597 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6818. Min Range: -5.6818
Max Act: 4.8380. Min Act: -0.1700
Data Index: 87863 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6818. Min Range: -5.6818
Max Act: 4.7443. Min Act: -0.1700
Data Index: 4233931 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6818. Min Range: -5.6818
Max Act: 4.7755. Min Act: -0.1700
Data Index: 4291659 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6818. Min Range: -5.6818
Max Act: 4.7755. Min Act: -0.1700
Data Index: 4160544 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6818. Min Range: -5.6818
Max Act: 4.7755. Min Act: -0.1700
Data Index: 2029040 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6818. Min Range: -5.6818
Max Act: 4.7443. Min Act: -0.1700
Data Index: 2721510 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6818. Min Range: -5.6818
Max Act: 4.7443. Min Act: -0.1700
Data Index: 8167161 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6818. Min Range: -5.6818
Max Act: 4.6818. Min Act: -0.1700
Data Index: 5966293 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6818. Min Range: -5.6818
Max Act: 4.6818. Min Act: -0.1700
Data Index: 1809961 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6818. Min Range: -5.6818
Max Act: 4.6505. Min Act: -0.1700
Data Index: 1370320 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6818. Min Range: -5.6818
Max Act: 4.6505. Min Act: -0.1700
Data Index: 7186410 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6818. Min Range: -5.6818
Max Act: 4.6818. Min Act: -0.1700
Data Index: 4595380 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6818. Min Range: -5.6818
Max Act: 4.6505. Min Act: -0.1700
Data Index: 7876777 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6818. Min Range: -5.6818
Max Act: 4.6505. Min Act: -0.1700
Data Index: 845840 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6818. Min Range: -5.6818
Max Act: 4.6193. Min Act: -0.1700
Data Index: 6606282 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6818. Min Range: -5.6818
Max Act: 4.6193. Min Act: -0.1700
Data Index: 4454980 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19