Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3633 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.2297. Min Act: -0.1700
Data Index: 8807019 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.1985. Min Act: -0.1700
Data Index: 6353507 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.2610. Min Act: -0.1700
Data Index: 5430663 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.1360. Min Act: -0.1700
Data Index: 344198 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.1047. Min Act: -0.1700
Data Index: 7589765 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.1360. Min Act: -0.1700
Data Index: 2769353 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.1047. Min Act: -0.1700
Data Index: 2578485 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0735. Min Act: -0.1700
Data Index: 2578484 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0735. Min Act: -0.1700
Data Index: 5564772 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0735. Min Act: -0.1700
Data Index: 6686224 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0735. Min Act: -0.1700
Data Index: 8642293 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0422. Min Act: -0.1700
Data Index: 6773541 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0422. Min Act: -0.1700
Data Index: 1848104 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0110. Min Act: -0.1700
Data Index: 6422550 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0110. Min Act: -0.1700
Data Index: 1685019 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0110. Min Act: -0.1700
Data Index: 3870733 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0110. Min Act: -0.1700
Data Index: 7868851 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0110. Min Act: -0.1700
Data Index: 3560727 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9797. Min Act: -0.1700
Data Index: 4208423 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9797. Min Act: -0.1700
Data Index: 3793365 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19