Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1458 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3300. Min Range: -6.3300
Max Act: 6.3300. Min Act: -0.1700
Data Index: 7918424 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3300. Min Range: -6.3300
Max Act: 6.3300. Min Act: -0.1700
Data Index: 2130450 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3300. Min Range: -6.3300
Max Act: 6.2362. Min Act: -0.1700
Data Index: 4740018 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3300. Min Range: -6.3300
Max Act: 6.2362. Min Act: -0.1700
Data Index: 6467423 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3300. Min Range: -6.3300
Max Act: 6.2050. Min Act: -0.1700
Data Index: 203561 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3300. Min Range: -6.3300
Max Act: 6.2050. Min Act: -0.1700
Data Index: 6003310 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3300. Min Range: -6.3300
Max Act: 6.1425. Min Act: -0.1700
Data Index: 203562 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3300. Min Range: -6.3300
Max Act: 6.1112. Min Act: -0.1700
Data Index: 7001702 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3300. Min Range: -6.3300
Max Act: 6.0800. Min Act: -0.1700
Data Index: 174391 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3300. Min Range: -6.3300
Max Act: 6.1112. Min Act: -0.1700
Data Index: 4740017 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3300. Min Range: -6.3300
Max Act: 6.0800. Min Act: -0.1700
Data Index: 6467427 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3300. Min Range: -6.3300
Max Act: 6.0487. Min Act: -0.1700
Data Index: 2409236 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3300. Min Range: -6.3300
Max Act: 6.0487. Min Act: -0.1700
Data Index: 7177876 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3300. Min Range: -6.3300
Max Act: 6.0487. Min Act: -0.1700
Data Index: 4451330 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3300. Min Range: -6.3300
Max Act: 6.0175. Min Act: -0.1700
Data Index: 6670738 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3300. Min Range: -6.3300
Max Act: 6.0487. Min Act: -0.1700
Data Index: 5101462 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3300. Min Range: -6.3300
Max Act: 5.9862. Min Act: -0.1700
Data Index: 1198875 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3300. Min Range: -6.3300
Max Act: 5.9862. Min Act: -0.1700
Data Index: 7974407 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3300. Min Range: -6.3300
Max Act: 5.9550. Min Act: -0.1700
Data Index: 5564715 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3300. Min Range: -6.3300
Max Act: 5.9862. Min Act: -0.1700
Data Index: 3317036 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19