Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3973. Min Act: -0.1700
Data Index: 2819950 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3973. Min Act: -0.1700
Data Index: 6470566 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3816. Min Act: -0.1700
Data Index: 2527102 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3973. Min Act: -0.1700
Data Index: 1747614 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3816. Min Act: -0.1700
Data Index: 7823441 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3816. Min Act: -0.1700
Data Index: 48972 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3660. Min Act: -0.1700
Data Index: 5747056 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3660. Min Act: -0.1700
Data Index: 8595349 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3660. Min Act: -0.1700
Data Index: 1431439 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3816. Min Act: -0.1700
Data Index: 6470567 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3503. Min Act: -0.1700
Data Index: 1887361 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3503. Min Act: -0.1700
Data Index: 1760449 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3503. Min Act: -0.1700
Data Index: 3337209 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3346. Min Act: -0.1700
Data Index: 5709340 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3189. Min Act: -0.1700
Data Index: 3788438 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3189. Min Act: -0.1700
Data Index: 2993474 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3346. Min Act: -0.1700
Data Index: 4155773 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3189. Min Act: -0.1700
Data Index: 6250467 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3189. Min Act: -0.1700
Data Index: 578270 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3973. Min Range: -3.3973
Max Act: 3.3032. Min Act: -0.1700
Data Index: 4451191 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19