Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2733 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.9414. Min Act: -0.1700
Data Index: 8370302 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.6914. Min Act: -0.1700
Data Index: 3680614 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.6289. Min Act: -0.1700
Data Index: 967996 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.6289. Min Act: -0.1700
Data Index: 1041818 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.5664. Min Act: -0.1700
Data Index: 1584144 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.5664. Min Act: -0.1700
Data Index: 1414463 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.5351. Min Act: -0.1700
Data Index: 5241795 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.5039. Min Act: -0.1700
Data Index: 814888 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.4726. Min Act: -0.1700
Data Index: 7096640 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.4726. Min Act: -0.1700
Data Index: 1898745 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.4726. Min Act: -0.1700
Data Index: 396108 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.4414. Min Act: -0.1700
Data Index: 5401062 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.4101. Min Act: -0.1700
Data Index: 8584614 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.4414. Min Act: -0.1700
Data Index: 422156 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.4101. Min Act: -0.1700
Data Index: 6053406 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.4414. Min Act: -0.1700
Data Index: 7180934 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.4101. Min Act: -0.1700
Data Index: 1328950 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.4101. Min Act: -0.1700
Data Index: 3313927 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.3789. Min Act: -0.1700
Data Index: 507915 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9414. Min Range: -7.9414
Max Act: 7.3476. Min Act: -0.1700
Data Index: 2407057 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19