Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2710 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.2553. Min Act: -0.1700
Data Index: 5650521 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.1928. Min Act: -0.1700
Data Index: 3488592 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.1928. Min Act: -0.1700
Data Index: 2464130 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.1928. Min Act: -0.1700
Data Index: 2020354 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.2240. Min Act: -0.1700
Data Index: 5072 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.1928. Min Act: -0.1700
Data Index: 6472183 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.1615. Min Act: -0.1700
Data Index: 2579866 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.1615. Min Act: -0.1700
Data Index: 4336104 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.1615. Min Act: -0.1700
Data Index: 7691763 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.1615. Min Act: -0.1700
Data Index: 4415678 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.1303. Min Act: -0.1700
Data Index: 5063152 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.1303. Min Act: -0.1700
Data Index: 6472181 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.1303. Min Act: -0.1700
Data Index: 6085585 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.0990. Min Act: -0.1700
Data Index: 3476214 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.1303. Min Act: -0.1700
Data Index: 2012589 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.0990. Min Act: -0.1700
Data Index: 6231261 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.0990. Min Act: -0.1700
Data Index: 3488600 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.0990. Min Act: -0.1700
Data Index: 3665971 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.0990. Min Act: -0.1700
Data Index: 3828360 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2553. Min Range: -5.2553
Max Act: 5.0678. Min Act: -0.1700
Data Index: 6598157 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19