Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 144 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0140. Min Range: -8.0140
Max Act: 8.0140. Min Act: -0.1700
Data Index: 5669010 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0140. Min Range: -8.0140
Max Act: 7.7015. Min Act: -0.1700
Data Index: 2790925 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0140. Min Range: -8.0140
Max Act: 7.7015. Min Act: -0.1700
Data Index: 2230703 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0140. Min Range: -8.0140
Max Act: 7.7015. Min Act: -0.1700
Data Index: 3198165 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0140. Min Range: -8.0140
Max Act: 7.6702. Min Act: -0.1700
Data Index: 5387884 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0140. Min Range: -8.0140
Max Act: 7.4515. Min Act: -0.1700
Data Index: 5387887 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0140. Min Range: -8.0140
Max Act: 7.4202. Min Act: -0.1700
Data Index: 1551789 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0140. Min Range: -8.0140
Max Act: 7.3890. Min Act: -0.1700
Data Index: 4329552 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0140. Min Range: -8.0140
Max Act: 7.3577. Min Act: -0.1700
Data Index: 5863138 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0140. Min Range: -8.0140
Max Act: 7.3265. Min Act: -0.1700
Data Index: 6208757 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0140. Min Range: -8.0140
Max Act: 7.3265. Min Act: -0.1700
Data Index: 8238606 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0140. Min Range: -8.0140
Max Act: 7.3265. Min Act: -0.1700
Data Index: 2599842 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0140. Min Range: -8.0140
Max Act: 7.2952. Min Act: -0.1700
Data Index: 5979981 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0140. Min Range: -8.0140
Max Act: 7.2952. Min Act: -0.1700
Data Index: 2208028 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0140. Min Range: -8.0140
Max Act: 7.2640. Min Act: -0.1700
Data Index: 3841802 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0140. Min Range: -8.0140
Max Act: 7.2640. Min Act: -0.1700
Data Index: 2652343 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0140. Min Range: -8.0140
Max Act: 7.2640. Min Act: -0.1700
Data Index: 2347697 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0140. Min Range: -8.0140
Max Act: 7.2327. Min Act: -0.1700
Data Index: 3916547 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0140. Min Range: -8.0140
Max Act: 7.2015. Min Act: -0.1700
Data Index: 1814853 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0140. Min Range: -8.0140
Max Act: 7.2015. Min Act: -0.1700
Data Index: 6939303 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19