Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2767 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0359. Min Act: -0.0004

Data Index: 15352 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0314. Min Act: -0.0004

Data Index: 1108171 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0345. Min Act: -0.0004

Data Index: 265366 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0324. Min Act: -0.0004

Data Index: 928575 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0321. Min Act: -0.0004

Data Index: 32387 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0308. Min Act: -0.0004

Data Index: 1111757 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0332. Min Act: -0.0004

Data Index: 500471 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0350. Min Act: -0.0004

Data Index: 1064259 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0342. Min Act: -0.0004

Data Index: 153548 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0319. Min Act: -0.0004

Data Index: 839453 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0316. Min Act: -0.0004

Data Index: 852267 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0329. Min Act: -0.0004

Data Index: 603174 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0307. Min Act: -0.0004

Data Index: 406658 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0307. Min Act: -0.0004

Data Index: 486868 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0300. Min Act: -0.0004

Data Index: 1403296 (Python Code)

Max Activating Token Index: 52

Text #15

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0326. Min Act: -0.0004

Data Index: 1026012 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0311. Min Act: -0.0004

Data Index: 1043866 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0311. Min Act: -0.0004

Data Index: 995224 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0311. Min Act: -0.0004

Data Index: 982237 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0311. Min Act: -0.0004

Data Index: 164917 (C4 (Web Text))

Max Activating Token Index: 3