Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5649 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.2429. Min Act: -0.1700
Data Index: 2277283 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.2272. Min Act: -0.1700
Data Index: 3352474 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.2272. Min Act: -0.1700
Data Index: 3493714 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.2272. Min Act: -0.1700
Data Index: 17639 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.2115. Min Act: -0.1700
Data Index: 1235252 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.2115. Min Act: -0.1700
Data Index: 6933399 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.1800. Min Act: -0.1700
Data Index: 1938761 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.1958. Min Act: -0.1700
Data Index: 6725521 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.1800. Min Act: -0.1700
Data Index: 1938777 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.1800. Min Act: -0.1700
Data Index: 2519421 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.1800. Min Act: -0.1700
Data Index: 45269 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.1800. Min Act: -0.1700
Data Index: 3968511 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.1800. Min Act: -0.1700
Data Index: 5250718 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.1800. Min Act: -0.1700
Data Index: 1938763 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.1800. Min Act: -0.1700
Data Index: 1879654 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.1643. Min Act: -0.1700
Data Index: 6656846 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.1486. Min Act: -0.1700
Data Index: 3772032 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.1643. Min Act: -0.1700
Data Index: 4926845 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.1643. Min Act: -0.1700
Data Index: 7179349 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2429. Min Range: -3.2429
Max Act: 3.1643. Min Act: -0.1700
Data Index: 1733637 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19