Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3793 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0366. Min Act: -0.0001

Data Index: 1284004 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0338. Min Act: -0.0001

Data Index: 123092 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0338. Min Act: -0.0001

Data Index: 172154 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0328. Min Act: -0.0001

Data Index: 866854 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0322. Min Act: -0.0001

Data Index: 374397 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1283636 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0327. Min Act: -0.0001

Data Index: 499553 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0311. Min Act: -0.0001

Data Index: 805074 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0317. Min Act: -0.0001

Data Index: 350407 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0311. Min Act: -0.0001

Data Index: 642725 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0310. Min Act: -0.0001

Data Index: 583775 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0308. Min Act: -0.0001

Data Index: 977184 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0301. Min Act: -0.0002

Data Index: 108280 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0302. Min Act: -0.0001

Data Index: 248903 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0305. Min Act: -0.0002

Data Index: 1106064 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0302. Min Act: -0.0001

Data Index: 415402 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0303. Min Act: -0.0001

Data Index: 1109730 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0293. Min Act: -0.0001

Data Index: 549078 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0289. Min Act: -0.0001

Data Index: 1185431 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0289. Min Act: -0.0001

Data Index: 859198 (C4 (Web Text))

Max Activating Token Index: 846