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

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

Neuron 3660 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0651. Min Act: -0.0000

Data Index: 1045982 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0428. Min Act: -0.0000

Data Index: 1512235 (Python Code)

Max Activating Token Index: 670

Text #2

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0340. Min Act: -0.0000

Data Index: 1604862 (Python Code)

Max Activating Token Index: 283

Text #3

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0357. Min Act: -0.0000

Data Index: 619801 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0347. Min Act: -0.0000

Data Index: 1372299 (Python Code)

Max Activating Token Index: 836

Text #5

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0356. Min Act: -0.0000

Data Index: 589729 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0365. Min Act: -0.0000

Data Index: 1087837 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0338. Min Act: -0.0000

Data Index: 374301 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0331. Min Act: -0.0000

Data Index: 1185386 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0314. Min Act: -0.0000

Data Index: 165140 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0320. Min Act: -0.0000

Data Index: 1461249 (Python Code)

Max Activating Token Index: 500

Text #11

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0311. Min Act: -0.0000

Data Index: 275633 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0290. Min Act: -0.0000

Data Index: 1549303 (Python Code)

Max Activating Token Index: 625

Text #13

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0315. Min Act: -0.0000

Data Index: 1590320 (Python Code)

Max Activating Token Index: 599

Text #14

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0318. Min Act: -0.0000

Data Index: 788742 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0304. Min Act: -0.0000

Data Index: 574473 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0313. Min Act: -0.0000

Data Index: 535027 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0289. Min Act: -0.0000

Data Index: 1148861 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0291. Min Act: -0.0000

Data Index: 867737 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0264. Min Act: -0.0000

Data Index: 376087 (C4 (Web Text))

Max Activating Token Index: 716