Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 368 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0358. Min Act: -0.0006

Data Index: 345434 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0342. Min Act: -0.0006

Data Index: 551882 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0325. Min Act: -0.0006

Data Index: 686913 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0315. Min Act: -0.0006

Data Index: 1279231 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0322. Min Act: -0.0006

Data Index: 533435 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0303. Min Act: -0.0006

Data Index: 664396 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0306. Min Act: -0.0006

Data Index: 1088091 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0304. Min Act: -0.0006

Data Index: 623816 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0298. Min Act: -0.0006

Data Index: 697941 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0285. Min Act: -0.0006

Data Index: 1290160 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0277. Min Act: -0.0006

Data Index: 1150730 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0272. Min Act: -0.0006

Data Index: 383313 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0283. Min Act: -0.0006

Data Index: 710402 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0282. Min Act: -0.0006

Data Index: 252951 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0280. Min Act: -0.0006

Data Index: 1314694 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0274. Min Act: -0.0006

Data Index: 563943 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0274. Min Act: -0.0006

Data Index: 451071 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0277. Min Act: -0.0006

Data Index: 1040965 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0277. Min Act: -0.0006

Data Index: 932934 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0281. Min Act: -0.0006

Data Index: 748897 (C4 (Web Text))

Max Activating Token Index: 318