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

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

Neuron 5814 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: 0.0372. Min Range: -0.0372

Max Act: 0.0367. Min Act: -0.0002

Data Index: 1104600 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0372. Min Act: -0.0002

Data Index: 745373 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0352. Min Act: -0.0002

Data Index: 625477 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0350. Min Act: -0.0002

Data Index: 272797 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1456559 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1067304 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0352. Min Act: -0.0002

Data Index: 610409 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0344. Min Act: -0.0002

Data Index: 527569 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1020960 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0340. Min Act: -0.0002

Data Index: 132771 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0340. Min Act: -0.0002

Data Index: 878272 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1092959 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0334. Min Act: -0.0002

Data Index: 559875 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1121676 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0336. Min Act: -0.0002

Data Index: 934050 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0329. Min Act: -0.0003

Data Index: 629265 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0331. Min Act: -0.0003

Data Index: 137140 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1424881 (Python Code)

Max Activating Token Index: 52

Text #18

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0332. Min Act: -0.0002

Data Index: 19624 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0324. Min Act: -0.0002

Data Index: 73226 (C4 (Web Text))

Max Activating Token Index: 215