Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3144 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.5234. Min Act: -0.1700
Data Index: 4764168 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.3672. Min Act: -0.1700
Data Index: 5624570 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.3359. Min Act: -0.1700
Data Index: 3128689 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.3047. Min Act: -0.1700
Data Index: 1894995 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.2422. Min Act: -0.1700
Data Index: 8379303 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.2422. Min Act: -0.1700
Data Index: 6057944 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.2109. Min Act: -0.1700
Data Index: 6184684 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.2109. Min Act: -0.1700
Data Index: 4956095 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.2422. Min Act: -0.1700
Data Index: 1828952 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.2109. Min Act: -0.1700
Data Index: 5229983 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.2109. Min Act: -0.1699
Data Index: 8176181 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.1797. Min Act: -0.1700
Data Index: 5776698 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.1797. Min Act: -0.1700
Data Index: 7292205 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.1172. Min Act: -0.1700
Data Index: 479949 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.1484. Min Act: -0.1700
Data Index: 8476554 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.1172. Min Act: -0.1700
Data Index: 6394842 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.0859. Min Act: -0.1700
Data Index: 4359579 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.0859. Min Act: -0.1700
Data Index: 2699221 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.0547. Min Act: -0.1700
Data Index: 1473143 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5234. Min Range: -6.5234
Max Act: 6.0547. Min Act: -0.1700
Data Index: 5286105 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19