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

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

Neuron 1948 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0467. Min Act: -0.0001

Data Index: 622749 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0475. Min Act: -0.0001

Data Index: 185758 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0417. Min Act: -0.0001

Data Index: 908655 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0400. Min Act: -0.0001

Data Index: 353643 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0367. Min Act: -0.0001

Data Index: 855392 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0363. Min Act: -0.0001

Data Index: 17969 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0368. Min Act: -0.0001

Data Index: 828190 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0352. Min Act: -0.0001

Data Index: 87632 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0338. Min Act: -0.0001

Data Index: 1274339 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0333. Min Act: -0.0001

Data Index: 179385 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0316. Min Act: -0.0001

Data Index: 1281786 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0322. Min Act: -0.0001

Data Index: 889062 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0308. Min Act: -0.0001

Data Index: 900962 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0329. Min Act: -0.0001

Data Index: 862718 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0287. Min Act: -0.0001

Data Index: 271546 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0305. Min Act: -0.0001

Data Index: 539163 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0283. Min Act: -0.0001

Data Index: 661894 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0312. Min Act: -0.0001

Data Index: 541225 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0276. Min Act: -0.0001

Data Index: 1257764 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1126059 (C4 (Web Text))

Max Activating Token Index: 929