Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3690 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.9609. Min Act: -0.1700
Data Index: 901519 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.9609. Min Act: -0.1700
Data Index: 5202284 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8359. Min Act: -0.1700
Data Index: 136526 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8671. Min Act: -0.1700
Data Index: 5863627 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8671. Min Act: -0.1700
Data Index: 1648261 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8671. Min Act: -0.1700
Data Index: 1867680 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8671. Min Act: -0.1700
Data Index: 5210548 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8671. Min Act: -0.1700
Data Index: 3444652 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8359. Min Act: -0.1700
Data Index: 5262409 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8046. Min Act: -0.1700
Data Index: 5214685 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8359. Min Act: -0.1700
Data Index: 1112614 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8359. Min Act: -0.1700
Data Index: 5097500 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8359. Min Act: -0.1700
Data Index: 5044853 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8359. Min Act: -0.1700
Data Index: 3796447 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8359. Min Act: -0.1700
Data Index: 2839097 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8359. Min Act: -0.1700
Data Index: 2800889 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8359. Min Act: -0.1700
Data Index: 2731917 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8359. Min Act: -0.1700
Data Index: 2622749 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8046. Min Act: -0.1700
Data Index: 1593404 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9609. Min Range: -4.9609
Max Act: 4.8359. Min Act: -0.1700
Data Index: 488481 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19