Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 169 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.5748. Min Act: -0.1700
Data Index: 6093157 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.5426. Min Act: -0.1700
Data Index: 6117839 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.5426. Min Act: -0.1700
Data Index: 8258266 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.5264. Min Act: -0.1700
Data Index: 4024379 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.4940. Min Act: -0.1700
Data Index: 1996555 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.4940. Min Act: -0.1700
Data Index: 3806049 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.5102. Min Act: -0.1700
Data Index: 93238 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.5102. Min Act: -0.1700
Data Index: 4054520 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.4940. Min Act: -0.1700
Data Index: 4900011 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.4940. Min Act: -0.1700
Data Index: 2800917 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.4778. Min Act: -0.1700
Data Index: 2027124 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.4616. Min Act: -0.1700
Data Index: 1962416 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.4616. Min Act: -0.1700
Data Index: 5623665 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.4616. Min Act: -0.1700
Data Index: 246 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.4616. Min Act: -0.1700
Data Index: 1339072 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.4453. Min Act: -0.1700
Data Index: 8240234 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.4453. Min Act: -0.1700
Data Index: 3580944 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.4290. Min Act: -0.1700
Data Index: 3869293 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.4453. Min Act: -0.1700
Data Index: 2102502 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5748. Min Range: -2.5748
Max Act: 2.3964. Min Act: -0.1700
Data Index: 5687229 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19