Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5550 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.7182. Min Act: -0.1700
Data Index: 1910874 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.6244. Min Act: -0.1700
Data Index: 96046 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.5307. Min Act: -0.1700
Data Index: 1763220 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.4369. Min Act: -0.1700
Data Index: 7436256 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.3119. Min Act: -0.1700
Data Index: 1303246 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.3119. Min Act: -0.1700
Data Index: 1871377 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.2807. Min Act: -0.1700
Data Index: 1455604 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.2807. Min Act: -0.1700
Data Index: 8425012 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.2494. Min Act: -0.1700
Data Index: 4779895 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.2807. Min Act: -0.1700
Data Index: 8054040 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.2182. Min Act: -0.1700
Data Index: 2593870 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.2182. Min Act: -0.1700
Data Index: 1662149 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.1557. Min Act: -0.1700
Data Index: 504155 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.1557. Min Act: -0.1700
Data Index: 5010840 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.1244. Min Act: -0.1700
Data Index: 4216932 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.1244. Min Act: -0.1700
Data Index: 8547390 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.0619. Min Act: -0.1700
Data Index: 7200852 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.0932. Min Act: -0.1700
Data Index: 3899073 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.0932. Min Act: -0.1700
Data Index: 3981635 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7182. Min Range: -6.7182
Max Act: 6.0619. Min Act: -0.1700
Data Index: 7610178 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19