Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3602 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.2796. Min Act: -0.1700
Data Index: 1635410 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.3109. Min Act: -0.1700
Data Index: 4859730 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.0921. Min Act: -0.1697
Data Index: 8367597 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.0609. Min Act: -0.1698
Data Index: 2681194 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.0296. Min Act: -0.1700
Data Index: 1708388 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.0296. Min Act: -0.1700
Data Index: 5332359 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3109. Min Range: -5.3109
Max Act: 4.9984. Min Act: -0.1700
Data Index: 5451966 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3109. Min Range: -5.3109
Max Act: 4.9984. Min Act: -0.1700
Data Index: 2096579 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3109. Min Range: -5.3109
Max Act: 4.9984. Min Act: -0.1700
Data Index: 370512 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3109. Min Range: -5.3109
Max Act: 4.9984. Min Act: -0.1700
Data Index: 4440486 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3109. Min Range: -5.3109
Max Act: 5.0296. Min Act: -0.1700
Data Index: 6965351 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3109. Min Range: -5.3109
Max Act: 4.9984. Min Act: -0.1700
Data Index: 2405156 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3109. Min Range: -5.3109
Max Act: 4.9984. Min Act: -0.1700
Data Index: 424785 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3109. Min Range: -5.3109
Max Act: 4.9984. Min Act: -0.1700
Data Index: 2481822 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3109. Min Range: -5.3109
Max Act: 4.9671. Min Act: -0.1700
Data Index: 3046307 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3109. Min Range: -5.3109
Max Act: 4.9671. Min Act: -0.1700
Data Index: 5451965 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3109. Min Range: -5.3109
Max Act: 4.9671. Min Act: -0.1700
Data Index: 5520930 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3109. Min Range: -5.3109
Max Act: 4.9671. Min Act: -0.1699
Data Index: 6252404 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3109. Min Range: -5.3109
Max Act: 4.9671. Min Act: -0.1700
Data Index: 7422978 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3109. Min Range: -5.3109
Max Act: 4.9671. Min Act: -0.1700
Data Index: 7883970 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19