Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2649 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.9757. Min Act: -0.1700
Data Index: 7530681 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.9444. Min Act: -0.1700
Data Index: 7530679 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.9444. Min Act: -0.1700
Data Index: 3895052 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.9444. Min Act: -0.1700
Data Index: 1890517 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.8819. Min Act: -0.1700
Data Index: 4633993 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.7882. Min Act: -0.1700
Data Index: 264212 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.7882. Min Act: -0.1700
Data Index: 7530680 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.6944. Min Act: -0.1700
Data Index: 3052243 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.6632. Min Act: -0.1700
Data Index: 8763624 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.6632. Min Act: -0.1700
Data Index: 4336546 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.6319. Min Act: -0.1700
Data Index: 8693384 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.6319. Min Act: -0.1700
Data Index: 1559451 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.6319. Min Act: -0.1700
Data Index: 1761586 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.6007. Min Act: -0.1700
Data Index: 4592156 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.6007. Min Act: -0.1700
Data Index: 4777505 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.5069. Min Act: -0.1700
Data Index: 1394742 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.5382. Min Act: -0.1700
Data Index: 8632876 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.5382. Min Act: -0.1700
Data Index: 956526 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.5382. Min Act: -0.1700
Data Index: 499507 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9757. Min Range: -6.9757
Max Act: 6.5382. Min Act: -0.1700
Data Index: 2898819 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19