Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 636 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.2861. Min Act: -0.1700
Data Index: 6727530 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.2236. Min Act: -0.1700
Data Index: 4790169 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.2548. Min Act: -0.1700
Data Index: 7626014 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.2236. Min Act: -0.1700
Data Index: 5640131 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.1923. Min Act: -0.1700
Data Index: 4297598 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.1923. Min Act: -0.1700
Data Index: 4407237 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.1923. Min Act: -0.1700
Data Index: 6343091 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.1923. Min Act: -0.1700
Data Index: 2960869 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.1923. Min Act: -0.1700
Data Index: 6727520 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.1923. Min Act: -0.1700
Data Index: 6109489 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.1611. Min Act: -0.1700
Data Index: 2392133 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.1923. Min Act: -0.1700
Data Index: 8814951 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.1611. Min Act: -0.1700
Data Index: 5785195 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.1611. Min Act: -0.1700
Data Index: 813111 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.1611. Min Act: -0.1700
Data Index: 8325909 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.1611. Min Act: -0.1700
Data Index: 5460513 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.1611. Min Act: -0.1700
Data Index: 4790165 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.1298. Min Act: -0.1700
Data Index: 1859143 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.1298. Min Act: -0.1700
Data Index: 941311 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2861. Min Range: -5.2861
Max Act: 5.1298. Min Act: -0.1700
Data Index: 6568832 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19