Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 716 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4241. Min Range: -4.4241
Max Act: 4.4241. Min Act: -0.1700
Data Index: 3541001 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4241. Min Range: -4.4241
Max Act: 4.1428. Min Act: -0.1700
Data Index: 2180413 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4241. Min Range: -4.4241
Max Act: 4.0491. Min Act: -0.1700
Data Index: 2587993 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4241. Min Range: -4.4241
Max Act: 4.0178. Min Act: -0.1700
Data Index: 8225194 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4241. Min Range: -4.4241
Max Act: 3.9553. Min Act: -0.1700
Data Index: 7104312 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4241. Min Range: -4.4241
Max Act: 3.9553. Min Act: -0.1700
Data Index: 3813032 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4241. Min Range: -4.4241
Max Act: 3.9397. Min Act: -0.1700
Data Index: 3578798 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4241. Min Range: -4.4241
Max Act: 3.8928. Min Act: -0.1700
Data Index: 3227314 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4241. Min Range: -4.4241
Max Act: 3.8771. Min Act: -0.1700
Data Index: 1074066 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4241. Min Range: -4.4241
Max Act: 3.8771. Min Act: -0.1700
Data Index: 3701341 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4241. Min Range: -4.4241
Max Act: 3.8302. Min Act: -0.1700
Data Index: 906690 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4241. Min Range: -4.4241
Max Act: 3.8459. Min Act: -0.1700
Data Index: 6121917 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4241. Min Range: -4.4241
Max Act: 3.8459. Min Act: -0.1700
Data Index: 4640271 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4241. Min Range: -4.4241
Max Act: 3.8615. Min Act: -0.1700
Data Index: 548816 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4241. Min Range: -4.4241
Max Act: 3.8459. Min Act: -0.1700
Data Index: 8224584 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4241. Min Range: -4.4241
Max Act: 3.8615. Min Act: -0.1700
Data Index: 3724745 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4241. Min Range: -4.4241
Max Act: 3.7989. Min Act: -0.1700
Data Index: 4823660 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4241. Min Range: -4.4241
Max Act: 3.7989. Min Act: -0.1700
Data Index: 6150663 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4241. Min Range: -4.4241
Max Act: 3.7677. Min Act: -0.1700
Data Index: 7787739 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4241. Min Range: -4.4241
Max Act: 3.7677. Min Act: -0.1700
Data Index: 44961 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19