Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3310 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.7349. Min Act: -0.1700
Data Index: 7213664 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.7189. Min Act: -0.1700
Data Index: 215326 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.7189. Min Act: -0.1700
Data Index: 5917937 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.6709. Min Act: -0.1700
Data Index: 7894451 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.6549. Min Act: -0.1700
Data Index: 3194093 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.6709. Min Act: -0.1700
Data Index: 2380641 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.6709. Min Act: -0.1700
Data Index: 7037174 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.6388. Min Act: -0.1700
Data Index: 5785666 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.6227. Min Act: -0.1700
Data Index: 7645933 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.6227. Min Act: -0.1700
Data Index: 951558 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.5906. Min Act: -0.1700
Data Index: 156605 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.6067. Min Act: -0.1700
Data Index: 1203848 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.6067. Min Act: -0.1700
Data Index: 3410007 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.5906. Min Act: -0.1700
Data Index: 4782535 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.6067. Min Act: -0.1700
Data Index: 2739714 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.5906. Min Act: -0.1700
Data Index: 5261374 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.6067. Min Act: -0.1700
Data Index: 2387891 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.5906. Min Act: -0.1700
Data Index: 840119 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.5744. Min Act: -0.1700
Data Index: 3267254 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7349. Min Range: -2.7349
Max Act: 2.5906. Min Act: -0.1700
Data Index: 7952573 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19