Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3609 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0396. Min Range: -4.0396
Max Act: 4.0396. Min Act: -0.1700
Data Index: 1252922 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.9458. Min Act: -0.1700
Data Index: 803750 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.8207. Min Act: -0.1700
Data Index: 8238326 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.7895. Min Act: -0.1700
Data Index: 4560449 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.8051. Min Act: -0.1700
Data Index: 5520601 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.8051. Min Act: -0.1700
Data Index: 5634081 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.7738. Min Act: -0.1700
Data Index: 3157923 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.7895. Min Act: -0.1700
Data Index: 6376205 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.7582. Min Act: -0.1700
Data Index: 8767411 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.7738. Min Act: -0.1700
Data Index: 77247 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.7582. Min Act: -0.1700
Data Index: 6636797 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.7269. Min Act: -0.1700
Data Index: 7266345 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.7582. Min Act: -0.1700
Data Index: 2422083 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.7269. Min Act: -0.1700
Data Index: 8533687 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.7426. Min Act: -0.1700
Data Index: 8494483 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.7269. Min Act: -0.1700
Data Index: 1426305 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.6800. Min Act: -0.1700
Data Index: 8201121 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.6800. Min Act: -0.1700
Data Index: 8013389 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.6643. Min Act: -0.1700
Data Index: 2802890 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.6643. Min Act: -0.1700
Data Index: 4082968 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19