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

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

Neuron 2512 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0442. Min Act: -0.0001

Data Index: 1018505 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0430. Min Act: -0.0001

Data Index: 596156 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0437. Min Act: -0.0001

Data Index: 797155 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0387. Min Act: -0.0001

Data Index: 934077 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0386. Min Act: -0.0001

Data Index: 522689 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0387. Min Act: -0.0001

Data Index: 355614 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0378. Min Act: -0.0001

Data Index: 1004345 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0383. Min Act: -0.0001

Data Index: 1309250 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0349. Min Act: -0.0001

Data Index: 1026991 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0347. Min Act: -0.0001

Data Index: 375822 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0328. Min Act: -0.0001

Data Index: 263715 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0349. Min Act: -0.0001

Data Index: 987487 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0332. Min Act: -0.0001

Data Index: 789301 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0311. Min Act: -0.0001

Data Index: 38915 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0348. Min Act: -0.0001

Data Index: 1204520 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0316. Min Act: -0.0001

Data Index: 1005966 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0323. Min Act: -0.0001

Data Index: 576774 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0330. Min Act: -0.0001

Data Index: 640282 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0321. Min Act: -0.0001

Data Index: 490885 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0320. Min Act: -0.0001

Data Index: 31432 (C4 (Web Text))

Max Activating Token Index: 211