Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2443 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1064. Min Range: -5.1064
Max Act: 5.1064. Min Act: -0.1700
Data Index: 6615753 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1064. Min Range: -5.1064
Max Act: 5.0127. Min Act: -0.1700
Data Index: 7994818 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1064. Min Range: -5.1064
Max Act: 4.9189. Min Act: -0.1700
Data Index: 973980 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1064. Min Range: -5.1064
Max Act: 4.8564. Min Act: -0.1700
Data Index: 3577160 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1064. Min Range: -5.1064
Max Act: 4.8252. Min Act: -0.1700
Data Index: 2640370 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1064. Min Range: -5.1064
Max Act: 4.8564. Min Act: -0.1700
Data Index: 6727424 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1064. Min Range: -5.1064
Max Act: 4.8252. Min Act: -0.1700
Data Index: 4668269 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1064. Min Range: -5.1064
Max Act: 4.8252. Min Act: -0.1700
Data Index: 2820772 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1064. Min Range: -5.1064
Max Act: 4.8252. Min Act: -0.1700
Data Index: 8660401 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1064. Min Range: -5.1064
Max Act: 4.7627. Min Act: -0.1700
Data Index: 619380 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1064. Min Range: -5.1064
Max Act: 4.7627. Min Act: -0.1700
Data Index: 434830 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1064. Min Range: -5.1064
Max Act: 4.7314. Min Act: -0.1700
Data Index: 8335232 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1064. Min Range: -5.1064
Max Act: 4.7002. Min Act: -0.1700
Data Index: 8323799 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1064. Min Range: -5.1064
Max Act: 4.7314. Min Act: -0.1700
Data Index: 8124770 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1064. Min Range: -5.1064
Max Act: 4.7002. Min Act: -0.1700
Data Index: 6466654 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1064. Min Range: -5.1064
Max Act: 4.7002. Min Act: -0.1700
Data Index: 5673676 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1064. Min Range: -5.1064
Max Act: 4.7002. Min Act: -0.1700
Data Index: 5966292 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1064. Min Range: -5.1064
Max Act: 4.7002. Min Act: -0.1700
Data Index: 568064 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1064. Min Range: -5.1064
Max Act: 4.7002. Min Act: -0.1700
Data Index: 6801497 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1064. Min Range: -5.1064
Max Act: 4.7002. Min Act: -0.1700
Data Index: 770820 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19