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

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

Neuron 5265 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0469. Min Act: -0.0000

Data Index: 1130096 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0447. Min Act: -0.0000

Data Index: 670172 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0383. Min Act: -0.0000

Data Index: 1320700 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0378. Min Act: -0.0000

Data Index: 1290530 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0342. Min Act: -0.0000

Data Index: 108122 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1283981 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0345. Min Act: -0.0000

Data Index: 502924 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0316. Min Act: -0.0000

Data Index: 854514 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0330. Min Act: -0.0000

Data Index: 676791 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0324. Min Act: -0.0000

Data Index: 1296194 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0319. Min Act: -0.0000

Data Index: 395014 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0300. Min Act: -0.0000

Data Index: 990274 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0310. Min Act: -0.0000

Data Index: 1004921 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0325. Min Act: -0.0000

Data Index: 1410806 (Python Code)

Max Activating Token Index: 949

Text #14

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0284. Min Act: -0.0000

Data Index: 79763 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0291. Min Act: -0.0000

Data Index: 972282 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0304. Min Act: -0.0000

Data Index: 1154695 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0289. Min Act: -0.0000

Data Index: 59532 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0304. Min Act: -0.0000

Data Index: 1285376 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0292. Min Act: -0.0000

Data Index: 793219 (C4 (Web Text))

Max Activating Token Index: 834