Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2391 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0071. Min Range: -5.0071
Max Act: 5.0071. Min Act: -0.1700
Data Index: 319269 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.9446. Min Act: -0.1700
Data Index: 6777613 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.9134. Min Act: -0.1700
Data Index: 1552097 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.8509. Min Act: -0.1700
Data Index: 5743041 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.8509. Min Act: -0.1700
Data Index: 2000335 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.7883. Min Act: -0.1700
Data Index: 512596 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.7883. Min Act: -0.1700
Data Index: 2718632 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.7883. Min Act: -0.1700
Data Index: 6853866 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.7258. Min Act: -0.1700
Data Index: 4412810 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.7258. Min Act: -0.1700
Data Index: 3741315 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.7258. Min Act: -0.1700
Data Index: 2523309 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.7258. Min Act: -0.1700
Data Index: 2465552 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.7258. Min Act: -0.1700
Data Index: 719868 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.6946. Min Act: -0.1700
Data Index: 3102653 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.6321. Min Act: -0.1700
Data Index: 8115052 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.6321. Min Act: -0.1700
Data Index: 7700053 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.6321. Min Act: -0.1700
Data Index: 7214149 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.6008. Min Act: -0.1700
Data Index: 65478 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.6008. Min Act: -0.1700
Data Index: 783050 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.6008. Min Act: -0.1700
Data Index: 5959719 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19