Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3705 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1159213 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0398. Min Act: -0.0001

Data Index: 590119 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0382. Min Act: -0.0001

Data Index: 605775 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0312. Min Act: -0.0001

Data Index: 472809 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0350. Min Act: -0.0001

Data Index: 782422 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0320. Min Act: -0.0001

Data Index: 385378 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0336. Min Act: -0.0001

Data Index: 923076 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0318. Min Act: -0.0000

Data Index: 568551 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0297. Min Act: -0.0001

Data Index: 180714 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0326. Min Act: -0.0000

Data Index: 1102023 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1167964 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0307. Min Act: -0.0001

Data Index: 760268 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0299. Min Act: -0.0000

Data Index: 652850 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0286. Min Act: -0.0001

Data Index: 738206 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0293. Min Act: -0.0001

Data Index: 397534 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0280. Min Act: -0.0001

Data Index: 1261052 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0290. Min Act: -0.0001

Data Index: 758314 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0289. Min Act: -0.0001

Data Index: 986261 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0300. Min Act: -0.0000

Data Index: 595966 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0300. Min Act: -0.0001

Data Index: 679810 (C4 (Web Text))

Max Activating Token Index: 179