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

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

Neuron 3422 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.2457. Min Act: -0.0001

Data Index: 1229609 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1045913 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.2209. Min Act: -0.0001

Data Index: 1081929 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1621. Min Act: -0.0000

Data Index: 755580 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1214875 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1622. Min Act: -0.0001

Data Index: 934178 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1469. Min Act: -0.0001

Data Index: 261126 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1638. Min Act: -0.0001

Data Index: 1163418 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1373. Min Act: -0.0001

Data Index: 1470065 (Python Code)

Max Activating Token Index: 945

Text #9

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1641. Min Act: -0.0001

Data Index: 959214 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1427. Min Act: -0.0001

Data Index: 1345128 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1207213 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1316. Min Act: -0.0001

Data Index: 854041 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1374. Min Act: -0.0001

Data Index: 303123 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1279. Min Act: -0.0001

Data Index: 1093513 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1248945 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1324. Min Act: -0.0001

Data Index: 583799 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1306. Min Act: -0.0001

Data Index: 443341 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1221. Min Act: -0.0001

Data Index: 167825 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1337. Min Act: -0.0000

Data Index: 309689 (C4 (Web Text))

Max Activating Token Index: 1012