Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2935 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1387. Min Range: -4.1387
Max Act: 4.1387. Min Act: -0.1700
Data Index: 7522732 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1387. Min Range: -4.1387
Max Act: 4.0449. Min Act: -0.1700
Data Index: 5947295 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1387. Min Range: -4.1387
Max Act: 4.0137. Min Act: -0.1700
Data Index: 7139557 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1387. Min Range: -4.1387
Max Act: 4.0137. Min Act: -0.1700
Data Index: 812862 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1387. Min Range: -4.1387
Max Act: 3.9824. Min Act: -0.1700
Data Index: 3443451 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1387. Min Range: -4.1387
Max Act: 3.9824. Min Act: -0.1700
Data Index: 2866448 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1387. Min Range: -4.1387
Max Act: 3.9824. Min Act: -0.1700
Data Index: 1532247 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1387. Min Range: -4.1387
Max Act: 3.9824. Min Act: -0.1700
Data Index: 7877853 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1387. Min Range: -4.1387
Max Act: 3.9512. Min Act: -0.1700
Data Index: 5753592 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1387. Min Range: -4.1387
Max Act: 3.9512. Min Act: -0.1700
Data Index: 169631 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1387. Min Range: -4.1387
Max Act: 3.9512. Min Act: -0.1700
Data Index: 6219015 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1387. Min Range: -4.1387
Max Act: 3.9512. Min Act: -0.1700
Data Index: 5984715 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1387. Min Range: -4.1387
Max Act: 3.9512. Min Act: -0.1700
Data Index: 1915308 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1387. Min Range: -4.1387
Max Act: 3.9199. Min Act: -0.1700
Data Index: 2162727 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1387. Min Range: -4.1387
Max Act: 3.9512. Min Act: -0.1700
Data Index: 2123169 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1387. Min Range: -4.1387
Max Act: 3.9512. Min Act: -0.1700
Data Index: 5283294 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1387. Min Range: -4.1387
Max Act: 3.9512. Min Act: -0.1700
Data Index: 4107440 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1387. Min Range: -4.1387
Max Act: 3.9512. Min Act: -0.1700
Data Index: 287944 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1387. Min Range: -4.1387
Max Act: 3.9512. Min Act: -0.1700
Data Index: 3961916 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1387. Min Range: -4.1387
Max Act: 3.9512. Min Act: -0.1700
Data Index: 839784 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19