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

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

Neuron 904 in Layer 1

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: 0.0324. Min Range: -0.0324

Max Act: 0.0315. Min Act: -0.0002

Data Index: 567698 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1244066 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0306. Min Act: -0.0002

Data Index: 536772 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1214393 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0275. Min Act: -0.0002

Data Index: 326990 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0274. Min Act: -0.0002

Data Index: 735720 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0271. Min Act: -0.0002

Data Index: 739224 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1341111 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1562577 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0266. Min Act: -0.0002

Data Index: 1566846 (Python Code)

Max Activating Token Index: 456

Text #10

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0264. Min Act: -0.0002

Data Index: 752218 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0257. Min Act: -0.0002

Data Index: 728019 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0261. Min Act: -0.0002

Data Index: 324397 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1226768 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0254. Min Act: -0.0002

Data Index: 1606651 (Python Code)

Max Activating Token Index: 1008

Text #15

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0250. Min Act: -0.0002

Data Index: 393312 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0249. Min Act: -0.0002

Data Index: 276432 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0250. Min Act: -0.0002

Data Index: 881836 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1242582 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0252. Min Act: -0.0002

Data Index: 950374 (C4 (Web Text))

Max Activating Token Index: 778