Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1224 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0324. Min Act: -0.0006

Data Index: 830811 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0319. Min Act: -0.0006

Data Index: 419093 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0317. Min Act: -0.0006

Data Index: 508596 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0316. Min Act: -0.0005

Data Index: 1005430 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0314. Min Act: -0.0006

Data Index: 946103 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0312. Min Act: -0.0006

Data Index: 123907 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0312. Min Act: -0.0006

Data Index: 426916 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0311. Min Act: -0.0006

Data Index: 685260 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0307. Min Act: -0.0006

Data Index: 114297 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0306. Min Act: -0.0006

Data Index: 777202 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0305. Min Act: -0.0006

Data Index: 669427 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0305. Min Act: -0.0006

Data Index: 1236260 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0301. Min Act: -0.0006

Data Index: 1061475 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0300. Min Act: -0.0006

Data Index: 1358531 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0306. Min Act: -0.0006

Data Index: 1313299 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0306. Min Act: -0.0006

Data Index: 882992 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0293. Min Act: -0.0006

Data Index: 191067 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0298. Min Act: -0.0006

Data Index: 157686 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0298. Min Act: -0.0006

Data Index: 307850 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0298. Min Act: -0.0006

Data Index: 1131265 (C4 (Web Text))

Max Activating Token Index: 731