Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3805 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6191. Min Range: -8.6191
Max Act: 8.6191. Min Act: -0.1700
Data Index: 2734172 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6191. Min Range: -8.6191
Max Act: 8.6191. Min Act: -0.1700
Data Index: 482257 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6191. Min Range: -8.6191
Max Act: 8.5566. Min Act: -0.1700
Data Index: 7900096 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6191. Min Range: -8.6191
Max Act: 8.5566. Min Act: -0.1700
Data Index: 4722341 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6191. Min Range: -8.6191
Max Act: 8.5566. Min Act: -0.1700
Data Index: 7900099 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6191. Min Range: -8.6191
Max Act: 8.5566. Min Act: -0.1700
Data Index: 7900095 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6191. Min Range: -8.6191
Max Act: 8.3691. Min Act: -0.1700
Data Index: 7451573 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6191. Min Range: -8.6191
Max Act: 8.2441. Min Act: -0.1700
Data Index: 4781527 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6191. Min Range: -8.6191
Max Act: 8.1816. Min Act: -0.1700
Data Index: 3086920 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6191. Min Range: -8.6191
Max Act: 8.1191. Min Act: -0.1700
Data Index: 5394288 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6191. Min Range: -8.6191
Max Act: 8.0566. Min Act: -0.1700
Data Index: 2735413 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6191. Min Range: -8.6191
Max Act: 8.0253. Min Act: -0.1700
Data Index: 5390957 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6191. Min Range: -8.6191
Max Act: 7.9628. Min Act: -0.1700
Data Index: 5962236 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6191. Min Range: -8.6191
Max Act: 7.9628. Min Act: -0.1700
Data Index: 4299868 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6191. Min Range: -8.6191
Max Act: 7.9628. Min Act: -0.1700
Data Index: 6508589 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6191. Min Range: -8.6191
Max Act: 7.9003. Min Act: -0.1700
Data Index: 748198 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6191. Min Range: -8.6191
Max Act: 7.9003. Min Act: -0.1700
Data Index: 6460712 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6191. Min Range: -8.6191
Max Act: 7.8691. Min Act: -0.1700
Data Index: 4440942 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6191. Min Range: -8.6191
Max Act: 7.8691. Min Act: -0.1700
Data Index: 1339785 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6191. Min Range: -8.6191
Max Act: 7.8066. Min Act: -0.1700
Data Index: 4783891 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19