Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6009 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6254. Min Range: -6.6254
Max Act: 6.6254. Min Act: -0.1700
Data Index: 2203120 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6254. Min Range: -6.6254
Max Act: 6.1566. Min Act: -0.1700
Data Index: 1896351 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6254. Min Range: -6.6254
Max Act: 6.1879. Min Act: -0.1700
Data Index: 6755932 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6254. Min Range: -6.6254
Max Act: 6.1566. Min Act: -0.1700
Data Index: 5174523 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6254. Min Range: -6.6254
Max Act: 6.1566. Min Act: -0.1700
Data Index: 4129784 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6254. Min Range: -6.6254
Max Act: 6.0941. Min Act: -0.1700
Data Index: 3853616 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6254. Min Range: -6.6254
Max Act: 6.0941. Min Act: -0.1700
Data Index: 1072038 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6254. Min Range: -6.6254
Max Act: 6.0941. Min Act: -0.1700
Data Index: 1252178 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6254. Min Range: -6.6254
Max Act: 6.0629. Min Act: -0.1700
Data Index: 4752617 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6254. Min Range: -6.6254
Max Act: 6.0629. Min Act: -0.1700
Data Index: 6945316 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6254. Min Range: -6.6254
Max Act: 6.0316. Min Act: -0.1700
Data Index: 669971 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6254. Min Range: -6.6254
Max Act: 6.0629. Min Act: -0.1700
Data Index: 3827754 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6254. Min Range: -6.6254
Max Act: 6.0316. Min Act: -0.1700
Data Index: 3576408 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6254. Min Range: -6.6254
Max Act: 6.0004. Min Act: -0.1700
Data Index: 7263318 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6254. Min Range: -6.6254
Max Act: 6.0004. Min Act: -0.1700
Data Index: 8483603 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6254. Min Range: -6.6254
Max Act: 6.0004. Min Act: -0.1700
Data Index: 1123281 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6254. Min Range: -6.6254
Max Act: 5.9691. Min Act: -0.1700
Data Index: 6504 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6254. Min Range: -6.6254
Max Act: 6.0004. Min Act: -0.1700
Data Index: 3193896 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6254. Min Range: -6.6254
Max Act: 5.9691. Min Act: -0.1700
Data Index: 1233511 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6254. Min Range: -6.6254
Max Act: 5.9691. Min Act: -0.1700
Data Index: 3470257 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19