Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1675 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.9324. Min Act: -0.0000

Data Index: 404204 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.8312. Min Act: -0.0000

Data Index: 69073 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1181493 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.6944. Min Act: -0.0000

Data Index: 798377 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.6717. Min Act: -0.0000

Data Index: 203312 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.6504. Min Act: -0.0000

Data Index: 355448 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.6039. Min Act: 0.0001

Data Index: 921830 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.6241. Min Act: -0.0000

Data Index: 575313 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.6302. Min Act: -0.0000

Data Index: 1298853 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.6720. Min Act: -0.0001

Data Index: 873818 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.6217. Min Act: -0.0000

Data Index: 712507 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.5102. Min Act: -0.0000

Data Index: 195284 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.6272. Min Act: -0.0000

Data Index: 143429 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1105853 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.5949. Min Act: -0.0000

Data Index: 407485 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.6209. Min Act: 0.0000

Data Index: 470978 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.5868. Min Act: -0.0000

Data Index: 108999 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.6152. Min Act: -0.0000

Data Index: 835198 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1262770 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.9324. Min Range: -0.9324

Max Act: 0.5532. Min Act: -0.0000

Data Index: 308203 (C4 (Web Text))

Max Activating Token Index: 812