Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4598 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2610. Min Range: -8.2610
Max Act: 8.2610. Min Act: -0.1700
Data Index: 5331459 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2610. Min Range: -8.2610
Max Act: 8.1985. Min Act: -0.1700
Data Index: 4344069 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2610. Min Range: -8.2610
Max Act: 8.0735. Min Act: -0.1700
Data Index: 2810696 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2610. Min Range: -8.2610
Max Act: 8.1360. Min Act: -0.1700
Data Index: 6141020 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2610. Min Range: -8.2610
Max Act: 8.1360. Min Act: -0.1700
Data Index: 1561799 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2610. Min Range: -8.2610
Max Act: 8.1360. Min Act: -0.1700
Data Index: 8515844 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2610. Min Range: -8.2610
Max Act: 8.1360. Min Act: -0.1700
Data Index: 3153034 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2610. Min Range: -8.2610
Max Act: 8.0735. Min Act: -0.1700
Data Index: 5153142 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2610. Min Range: -8.2610
Max Act: 8.0735. Min Act: -0.1700
Data Index: 4404916 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2610. Min Range: -8.2610
Max Act: 8.0735. Min Act: -0.1700
Data Index: 2099659 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2610. Min Range: -8.2610
Max Act: 8.0735. Min Act: -0.1700
Data Index: 5994390 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2610. Min Range: -8.2610
Max Act: 8.0110. Min Act: -0.1700
Data Index: 1603429 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2610. Min Range: -8.2610
Max Act: 8.0110. Min Act: -0.1700
Data Index: 4049429 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2610. Min Range: -8.2610
Max Act: 8.0110. Min Act: -0.1700
Data Index: 398955 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2610. Min Range: -8.2610
Max Act: 7.9485. Min Act: -0.1700
Data Index: 1222487 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2610. Min Range: -8.2610
Max Act: 7.8860. Min Act: -0.1700
Data Index: 5298084 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2610. Min Range: -8.2610
Max Act: 7.8860. Min Act: -0.1700
Data Index: 1856314 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2610. Min Range: -8.2610
Max Act: 7.8547. Min Act: -0.1700
Data Index: 6833385 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2610. Min Range: -8.2610
Max Act: 7.8547. Min Act: -0.1700
Data Index: 6129461 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2610. Min Range: -8.2610
Max Act: 7.8235. Min Act: -0.1700
Data Index: 5220154 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19