Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2439 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0291. Min Act: -0.0001

Data Index: 727890 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0297. Min Act: -0.0001

Data Index: 118107 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0302. Min Act: -0.0001

Data Index: 782051 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1043677 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0297. Min Act: -0.0001

Data Index: 509120 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0274. Min Act: -0.0001

Data Index: 385890 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0282. Min Act: -0.0001

Data Index: 958170 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0296. Min Act: -0.0001

Data Index: 311776 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0293. Min Act: -0.0001

Data Index: 1293849 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0284. Min Act: -0.0001

Data Index: 471950 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0278. Min Act: -0.0001

Data Index: 837581 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1470446 (Python Code)

Max Activating Token Index: 567

Text #12

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1290476 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0278. Min Act: -0.0001

Data Index: 1273628 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0281. Min Act: -0.0001

Data Index: 748297 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0266. Min Act: -0.0001

Data Index: 856289 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0265. Min Act: -0.0001

Data Index: 1221208 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0270. Min Act: -0.0001

Data Index: 437253 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0265. Min Act: -0.0001

Data Index: 675216 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0279. Min Act: -0.0001

Data Index: 75632 (C4 (Web Text))

Max Activating Token Index: 343