Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4246 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.9481. Min Act: -0.1700
Data Index: 1643191 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.6981. Min Act: -0.1700
Data Index: 2636169 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.6356. Min Act: -0.1700
Data Index: 1859198 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.5731. Min Act: -0.1700
Data Index: 6745468 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.5731. Min Act: -0.1700
Data Index: 3181596 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.5731. Min Act: -0.1700
Data Index: 8020826 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.5106. Min Act: -0.1700
Data Index: 5062072 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.5106. Min Act: -0.1700
Data Index: 4717331 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.5106. Min Act: -0.1700
Data Index: 8669904 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.4481. Min Act: -0.1700
Data Index: 7168578 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.4481. Min Act: -0.1700
Data Index: 5923367 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.3856. Min Act: -0.1700
Data Index: 6198791 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.3231. Min Act: -0.1700
Data Index: 6849099 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.3231. Min Act: -0.1700
Data Index: 6056754 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.3231. Min Act: -0.1700
Data Index: 8277951 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.2606. Min Act: -0.1700
Data Index: 6218012 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.2606. Min Act: -0.1700
Data Index: 3373319 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.2606. Min Act: -0.1700
Data Index: 3747584 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.1981. Min Act: -0.1700
Data Index: 5053327 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9481. Min Range: -8.9481
Max Act: 8.2606. Min Act: -0.1700
Data Index: 941699 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19