Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6361. Min Range: -8.6361
Max Act: 8.6361. Min Act: -0.1700
Data Index: 3599459 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6361. Min Range: -8.6361
Max Act: 8.3236. Min Act: -0.1700
Data Index: 4892473 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6361. Min Range: -8.6361
Max Act: 8.3236. Min Act: -0.1700
Data Index: 6589585 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6361. Min Range: -8.6361
Max Act: 8.2611. Min Act: -0.1700
Data Index: 4389961 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6361. Min Range: -8.6361
Max Act: 8.2611. Min Act: -0.1700
Data Index: 42320 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6361. Min Range: -8.6361
Max Act: 8.1986. Min Act: -0.1700
Data Index: 4118151 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6361. Min Range: -8.6361
Max Act: 8.1986. Min Act: -0.1700
Data Index: 6325925 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6361. Min Range: -8.6361
Max Act: 8.1986. Min Act: -0.1700
Data Index: 5072900 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6361. Min Range: -8.6361
Max Act: 8.1361. Min Act: -0.1700
Data Index: 4197212 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6361. Min Range: -8.6361
Max Act: 8.0736. Min Act: -0.1700
Data Index: 7003534 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6361. Min Range: -8.6361
Max Act: 8.0736. Min Act: -0.1700
Data Index: 1575136 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6361. Min Range: -8.6361
Max Act: 7.9486. Min Act: -0.1700
Data Index: 4508507 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6361. Min Range: -8.6361
Max Act: 7.9486. Min Act: -0.1700
Data Index: 6666648 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6361. Min Range: -8.6361
Max Act: 7.9486. Min Act: -0.1700
Data Index: 6560940 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6361. Min Range: -8.6361
Max Act: 7.9486. Min Act: -0.1700
Data Index: 6532439 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6361. Min Range: -8.6361
Max Act: 7.8861. Min Act: -0.1700
Data Index: 4108920 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6361. Min Range: -8.6361
Max Act: 7.8861. Min Act: -0.1700
Data Index: 3768855 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6361. Min Range: -8.6361
Max Act: 7.8861. Min Act: -0.1700
Data Index: 4292670 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6361. Min Range: -8.6361
Max Act: 7.9486. Min Act: -0.1700
Data Index: 1719217 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6361. Min Range: -8.6361
Max Act: 7.8236. Min Act: -0.1700
Data Index: 5695937 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19