Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1703 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.6387. Min Act: -0.1700
Data Index: 5518671 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.5762. Min Act: -0.1700
Data Index: 8449937 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.4825. Min Act: -0.1700
Data Index: 2735254 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.3887. Min Act: -0.1700
Data Index: 242081 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.3575. Min Act: -0.1700
Data Index: 6394815 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.3262. Min Act: -0.1700
Data Index: 402538 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.3262. Min Act: -0.1700
Data Index: 5648356 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.2637. Min Act: -0.1700
Data Index: 1546522 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.2325. Min Act: -0.1700
Data Index: 2568159 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.2637. Min Act: -0.1700
Data Index: 7008282 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.2325. Min Act: -0.1700
Data Index: 1689485 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.2637. Min Act: -0.1700
Data Index: 6163827 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.2950. Min Act: -0.1700
Data Index: 535383 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.2325. Min Act: -0.1700
Data Index: 3687367 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.2325. Min Act: -0.1700
Data Index: 2747625 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.2012. Min Act: -0.1700
Data Index: 7557323 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.2012. Min Act: -0.1700
Data Index: 8134538 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.1700. Min Act: -0.1700
Data Index: 4970149 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.1387. Min Act: -0.1700
Data Index: 1589783 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.1387. Min Act: -0.1700
Data Index: 5414283 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19