Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 506 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.6408. Min Act: -0.1700
Data Index: 6815045 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.6096. Min Act: -0.1700
Data Index: 8467603 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.6096. Min Act: -0.1700
Data Index: 2876133 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.5158. Min Act: -0.1700
Data Index: 2014910 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.5158. Min Act: -0.1700
Data Index: 8738715 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.3596. Min Act: -0.1700
Data Index: 2705381 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.3596. Min Act: -0.1700
Data Index: 1650106 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.3596. Min Act: -0.1700
Data Index: 6769003 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.2971. Min Act: -0.1700
Data Index: 4197837 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.2658. Min Act: -0.1700
Data Index: 3049953 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.2658. Min Act: -0.1700
Data Index: 7213504 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.2658. Min Act: -0.1700
Data Index: 7518242 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.2658. Min Act: -0.1700
Data Index: 7194530 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.2346. Min Act: -0.1700
Data Index: 5200807 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.2346. Min Act: -0.1700
Data Index: 3984121 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.2658. Min Act: -0.1700
Data Index: 649787 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.2346. Min Act: -0.1700
Data Index: 2392528 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.2658. Min Act: -0.1700
Data Index: 5740084 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.2346. Min Act: -0.1700
Data Index: 4920595 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6408. Min Range: -4.6408
Max Act: 4.2346. Min Act: -0.1700
Data Index: 7824032 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19