Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5337 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.8516. Min Act: -0.0000

Data Index: 260186 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.8103. Min Act: -0.0000

Data Index: 352756 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1074937 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1156992 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6653. Min Act: 0.0002

Data Index: 114819 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6550. Min Act: -0.0000

Data Index: 1151818 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6540. Min Act: -0.0000

Data Index: 1260357 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6576. Min Act: -0.0000

Data Index: 947430 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6750. Min Act: -0.0000

Data Index: 558171 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6411. Min Act: -0.0000

Data Index: 728272 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6202. Min Act: -0.0000

Data Index: 340669 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1251947 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6538. Min Act: -0.0000

Data Index: 832034 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.5838. Min Act: 0.0001

Data Index: 1109902 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.5594. Min Act: 0.0000

Data Index: 375067 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.5689. Min Act: -0.0000

Data Index: 263092 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.5472. Min Act: -0.0000

Data Index: 393764 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.5388. Min Act: -0.0000

Data Index: 856950 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.5223. Min Act: 0.0001

Data Index: 7723 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1023740 (C4 (Web Text))

Max Activating Token Index: 231