Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5126 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8616. Min Range: -8.8616
Max Act: 8.8616. Min Act: -0.1700
Data Index: 2779719 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8616. Min Range: -8.8616
Max Act: 8.2678. Min Act: -0.1700
Data Index: 934710 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8616. Min Range: -8.8616
Max Act: 8.0178. Min Act: -0.1700
Data Index: 4340419 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8616. Min Range: -8.8616
Max Act: 7.8616. Min Act: -0.1700
Data Index: 5633388 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8616. Min Range: -8.8616
Max Act: 7.6428. Min Act: -0.1700
Data Index: 2639351 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8616. Min Range: -8.8616
Max Act: 7.6428. Min Act: -0.1700
Data Index: 8361283 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8616. Min Range: -8.8616
Max Act: 7.6116. Min Act: -0.1700
Data Index: 1601173 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8616. Min Range: -8.8616
Max Act: 7.5491. Min Act: -0.1700
Data Index: 4841943 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8616. Min Range: -8.8616
Max Act: 7.5803. Min Act: -0.1700
Data Index: 3511028 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8616. Min Range: -8.8616
Max Act: 7.5803. Min Act: -0.1700
Data Index: 3466421 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8616. Min Range: -8.8616
Max Act: 7.5491. Min Act: -0.1700
Data Index: 6406478 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8616. Min Range: -8.8616
Max Act: 7.5178. Min Act: -0.1700
Data Index: 3152012 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8616. Min Range: -8.8616
Max Act: 7.4866. Min Act: -0.1700
Data Index: 7732640 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8616. Min Range: -8.8616
Max Act: 7.4553. Min Act: -0.1700
Data Index: 2890581 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8616. Min Range: -8.8616
Max Act: 7.4553. Min Act: -0.1700
Data Index: 8215984 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8616. Min Range: -8.8616
Max Act: 7.4553. Min Act: -0.1700
Data Index: 1924543 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8616. Min Range: -8.8616
Max Act: 7.4553. Min Act: -0.1700
Data Index: 4371874 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8616. Min Range: -8.8616
Max Act: 7.4553. Min Act: -0.1700
Data Index: 8023558 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8616. Min Range: -8.8616
Max Act: 7.4241. Min Act: -0.1700
Data Index: 6101546 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8616. Min Range: -8.8616
Max Act: 7.3928. Min Act: -0.1700
Data Index: 3538438 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19