Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 908 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.9275. Min Act: -0.1700
Data Index: 6180060 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.8806. Min Act: -0.1700
Data Index: 8424981 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.8180. Min Act: -0.1700
Data Index: 5585266 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.7711. Min Act: -0.1700
Data Index: 3926646 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.7086. Min Act: -0.1700
Data Index: 4822839 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.6460. Min Act: -0.1700
Data Index: 4485722 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.6460. Min Act: -0.1700
Data Index: 1516139 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.6460. Min Act: -0.1700
Data Index: 30590 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.6616. Min Act: -0.1700
Data Index: 2445561 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.6460. Min Act: -0.1700
Data Index: 5074728 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.6303. Min Act: -0.1700
Data Index: 4035985 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.6303. Min Act: -0.1700
Data Index: 1757683 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.5834. Min Act: -0.1700
Data Index: 3887661 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.5834. Min Act: -0.1700
Data Index: 8358518 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.5677. Min Act: -0.1700
Data Index: 5899507 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.5521. Min Act: -0.1700
Data Index: 3368116 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.5521. Min Act: -0.1700
Data Index: 2055497 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.5521. Min Act: -0.1700
Data Index: 5247773 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.5521. Min Act: -0.1700
Data Index: 4396383 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9275. Min Range: -3.9275
Max Act: 3.5208. Min Act: -0.1700
Data Index: 4822841 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19