Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 612 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.7348. Min Act: -0.1700
Data Index: 3947185 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.7348. Min Act: -0.1700
Data Index: 5754767 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.7348. Min Act: -0.1700
Data Index: 1540877 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.7036. Min Act: -0.1700
Data Index: 6422429 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.7036. Min Act: -0.1700
Data Index: 6123900 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.6411. Min Act: -0.1700
Data Index: 2858200 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.6723. Min Act: -0.1700
Data Index: 2311046 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.6411. Min Act: -0.1700
Data Index: 2601909 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.6098. Min Act: -0.1700
Data Index: 1161478 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.6411. Min Act: -0.1700
Data Index: 2631598 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.6098. Min Act: -0.1700
Data Index: 8539912 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.6098. Min Act: -0.1700
Data Index: 6660851 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.6098. Min Act: -0.1700
Data Index: 7274739 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.5786. Min Act: -0.1700
Data Index: 1810900 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.5473. Min Act: -0.1700
Data Index: 7232297 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.5161. Min Act: -0.1700
Data Index: 3091288 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.5473. Min Act: -0.1700
Data Index: 815809 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.5473. Min Act: -0.1700
Data Index: 2936314 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.5161. Min Act: -0.1700
Data Index: 179994 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7348. Min Range: -4.7348
Max Act: 4.5161. Min Act: -0.1700
Data Index: 4121840 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19