Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.6419. Min Act: -0.1700
Data Index: 5525095 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.5936. Min Act: -0.1700
Data Index: 7770713 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.5775. Min Act: -0.1700
Data Index: 4374716 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.6097. Min Act: -0.1700
Data Index: 4374712 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.5291. Min Act: -0.1700
Data Index: 1325762 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.5291. Min Act: -0.1700
Data Index: 4776813 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.5453. Min Act: -0.1700
Data Index: 524388 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.5291. Min Act: -0.1700
Data Index: 4097857 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.5129. Min Act: -0.1700
Data Index: 6596913 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.4967. Min Act: -0.1700
Data Index: 8155107 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.4967. Min Act: -0.1700
Data Index: 3296328 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.4967. Min Act: -0.1700
Data Index: 6843288 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.4805. Min Act: -0.1700
Data Index: 7140025 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.4805. Min Act: -0.1700
Data Index: 214585 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.4805. Min Act: -0.1700
Data Index: 1046471 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.4805. Min Act: -0.1700
Data Index: 5754558 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.4318. Min Act: -0.1700
Data Index: 5266205 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.4480. Min Act: -0.1700
Data Index: 3084653 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.4318. Min Act: -0.1700
Data Index: 4955830 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6419. Min Range: -2.6419
Max Act: 2.4480. Min Act: -0.1700
Data Index: 5538417 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19