Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4352 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0897. Min Range: -5.0897
Max Act: 5.0897. Min Act: -0.1700
Data Index: 7074013 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0897. Min Range: -5.0897
Max Act: 5.0584. Min Act: -0.1700
Data Index: 3128346 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0897. Min Range: -5.0897
Max Act: 4.9022. Min Act: -0.1700
Data Index: 2683392 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0897. Min Range: -5.0897
Max Act: 4.9022. Min Act: -0.1700
Data Index: 3167391 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0897. Min Range: -5.0897
Max Act: 4.9022. Min Act: -0.1700
Data Index: 8257991 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0897. Min Range: -5.0897
Max Act: 4.8397. Min Act: -0.1700
Data Index: 3242143 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0897. Min Range: -5.0897
Max Act: 4.8397. Min Act: -0.1700
Data Index: 2658834 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0897. Min Range: -5.0897
Max Act: 4.8397. Min Act: -0.1700
Data Index: 1134768 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0897. Min Range: -5.0897
Max Act: 4.8709. Min Act: -0.1700
Data Index: 2907619 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0897. Min Range: -5.0897
Max Act: 4.8397. Min Act: -0.1700
Data Index: 1342379 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0897. Min Range: -5.0897
Max Act: 4.8397. Min Act: -0.1700
Data Index: 418358 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0897. Min Range: -5.0897
Max Act: 4.8397. Min Act: -0.1700
Data Index: 6382706 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0897. Min Range: -5.0897
Max Act: 4.8084. Min Act: -0.1700
Data Index: 678078 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0897. Min Range: -5.0897
Max Act: 4.8084. Min Act: -0.1700
Data Index: 5000584 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0897. Min Range: -5.0897
Max Act: 4.8084. Min Act: -0.1700
Data Index: 1106036 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0897. Min Range: -5.0897
Max Act: 4.8084. Min Act: -0.1700
Data Index: 273646 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0897. Min Range: -5.0897
Max Act: 4.8084. Min Act: -0.1700
Data Index: 2502707 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0897. Min Range: -5.0897
Max Act: 4.8084. Min Act: -0.1700
Data Index: 2507432 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0897. Min Range: -5.0897
Max Act: 4.8084. Min Act: -0.1700
Data Index: 3907474 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0897. Min Range: -5.0897
Max Act: 4.7772. Min Act: -0.1700
Data Index: 1970954 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19