Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5321 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0343. Min Range: -8.0343
Max Act: 8.0343. Min Act: -0.1700
Data Index: 2782965 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0343. Min Range: -8.0343
Max Act: 7.5343. Min Act: -0.1700
Data Index: 4779381 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0343. Min Range: -8.0343
Max Act: 7.5030. Min Act: -0.1700
Data Index: 3424771 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0343. Min Range: -8.0343
Max Act: 7.4718. Min Act: -0.1700
Data Index: 6070961 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0343. Min Range: -8.0343
Max Act: 7.4405. Min Act: -0.1700
Data Index: 8488561 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0343. Min Range: -8.0343
Max Act: 7.3780. Min Act: -0.1700
Data Index: 1568172 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0343. Min Range: -8.0343
Max Act: 7.4093. Min Act: -0.1700
Data Index: 3411867 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0343. Min Range: -8.0343
Max Act: 7.3468. Min Act: -0.1700
Data Index: 1886720 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0343. Min Range: -8.0343
Max Act: 7.2530. Min Act: -0.1700
Data Index: 7750520 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0343. Min Range: -8.0343
Max Act: 7.2843. Min Act: -0.1700
Data Index: 7124507 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0343. Min Range: -8.0343
Max Act: 7.2218. Min Act: -0.1700
Data Index: 5858419 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0343. Min Range: -8.0343
Max Act: 7.1905. Min Act: -0.1700
Data Index: 8446651 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0343. Min Range: -8.0343
Max Act: 7.1593. Min Act: -0.1700
Data Index: 283794 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0343. Min Range: -8.0343
Max Act: 7.1280. Min Act: -0.1700
Data Index: 965954 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0343. Min Range: -8.0343
Max Act: 7.1280. Min Act: -0.1700
Data Index: 6751006 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0343. Min Range: -8.0343
Max Act: 7.1280. Min Act: -0.1700
Data Index: 1245257 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0343. Min Range: -8.0343
Max Act: 7.0968. Min Act: -0.1700
Data Index: 2114276 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0343. Min Range: -8.0343
Max Act: 7.0655. Min Act: -0.1700
Data Index: 4413424 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0343. Min Range: -8.0343
Max Act: 7.0968. Min Act: -0.1700
Data Index: 1317763 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0343. Min Range: -8.0343
Max Act: 7.0655. Min Act: -0.1700
Data Index: 5869219 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19