Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2495 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.9611. Min Act: -0.1700
Data Index: 3094461 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.9611. Min Act: -0.1700
Data Index: 4522720 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.9298. Min Act: -0.1700
Data Index: 2378845 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.8673. Min Act: -0.1700
Data Index: 1465833 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.8361. Min Act: -0.1700
Data Index: 3024964 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.8361. Min Act: -0.1700
Data Index: 7575590 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.8673. Min Act: -0.1700
Data Index: 4161840 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.8361. Min Act: -0.1700
Data Index: 4871210 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.8048. Min Act: -0.1700
Data Index: 7053986 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.8048. Min Act: -0.1700
Data Index: 6294742 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.8048. Min Act: -0.1700
Data Index: 471201 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.7423. Min Act: -0.1700
Data Index: 8464457 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.7423. Min Act: -0.1700
Data Index: 592219 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.7111. Min Act: -0.1700
Data Index: 3835065 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.7423. Min Act: -0.1700
Data Index: 7535674 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.6486. Min Act: -0.1700
Data Index: 8692812 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.6798. Min Act: -0.1700
Data Index: 5259004 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.6486. Min Act: -0.1700
Data Index: 2118549 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.6173. Min Act: -0.1700
Data Index: 5287243 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9611. Min Range: -4.9611
Max Act: 4.6173. Min Act: -0.1700
Data Index: 4787857 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19