Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3643 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.7548. Min Act: -0.1700
Data Index: 5949279 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.7548. Min Act: -0.1700
Data Index: 2748358 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.7548. Min Act: -0.1700
Data Index: 5591204 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.7236. Min Act: -0.1700
Data Index: 3206670 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.6610. Min Act: -0.1700
Data Index: 1707965 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.6610. Min Act: -0.1700
Data Index: 2528565 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.6297. Min Act: -0.1700
Data Index: 4329472 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.5984. Min Act: -0.1700
Data Index: 1761747 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.5984. Min Act: -0.1700
Data Index: 4245337 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.5984. Min Act: -0.1700
Data Index: 5358 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.5984. Min Act: -0.1700
Data Index: 7574 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.5984. Min Act: -0.1700
Data Index: 8818768 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.5671. Min Act: -0.1700
Data Index: 4318765 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.5671. Min Act: -0.1700
Data Index: 53796 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.5671. Min Act: -0.1700
Data Index: 3091608 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.5358. Min Act: -0.1700
Data Index: 409318 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.5358. Min Act: -0.1700
Data Index: 5760227 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.5358. Min Act: -0.1700
Data Index: 7585569 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.5358. Min Act: -0.1700
Data Index: 2659595 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7548. Min Range: -3.7548
Max Act: 3.5044. Min Act: -0.1700
Data Index: 3764437 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19