Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2655 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.9552. Min Act: -0.1700
Data Index: 3568032 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.5177. Min Act: -0.1700
Data Index: 725433 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.5489. Min Act: -0.1700
Data Index: 6745404 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.3927. Min Act: -0.1700
Data Index: 600801 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.2364. Min Act: -0.1700
Data Index: 4272010 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.2052. Min Act: -0.1700
Data Index: 6207193 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.1739. Min Act: -0.1700
Data Index: 4600557 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.1427. Min Act: -0.1700
Data Index: 6829086 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.1427. Min Act: -0.1700
Data Index: 5170724 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.1114. Min Act: -0.1700
Data Index: 384574 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.1114. Min Act: -0.1700
Data Index: 3136276 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.1114. Min Act: -0.1700
Data Index: 3856641 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.1114. Min Act: -0.1700
Data Index: 853516 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.0802. Min Act: -0.1700
Data Index: 7058798 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.0802. Min Act: -0.1700
Data Index: 7292099 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.0802. Min Act: -0.1700
Data Index: 4772510 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.0802. Min Act: -0.1700
Data Index: 4075726 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.0802. Min Act: -0.1700
Data Index: 4160545 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.0177. Min Act: -0.1700
Data Index: 4984752 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9552. Min Range: -6.9552
Max Act: 6.0489. Min Act: -0.1700
Data Index: 5013482 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19