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

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

Neuron 721 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2520. Min Act: -0.0001

Data Index: 204504 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2696. Min Act: -0.0001

Data Index: 1608898 (Python Code)

Max Activating Token Index: 349

Text #2

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2487. Min Act: -0.0001

Data Index: 717540 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1465451 (Python Code)

Max Activating Token Index: 184

Text #4

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2514. Min Act: -0.0001

Data Index: 713425 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2418. Min Act: -0.0001

Data Index: 1109055 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2302. Min Act: -0.0001

Data Index: 483925 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2359. Min Act: -0.0001

Data Index: 1061904 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2407. Min Act: -0.0001

Data Index: 491006 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2485. Min Act: -0.0001

Data Index: 1247245 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2307. Min Act: -0.0001

Data Index: 344745 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2308. Min Act: -0.0001

Data Index: 544782 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2384. Min Act: -0.0001

Data Index: 72511 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2388. Min Act: -0.0001

Data Index: 360279 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2305. Min Act: -0.0001

Data Index: 670280 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2298. Min Act: -0.0001

Data Index: 1028460 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2357. Min Act: -0.0001

Data Index: 992540 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2196. Min Act: -0.0001

Data Index: 469641 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2289. Min Act: -0.0001

Data Index: 1394989 (Python Code)

Max Activating Token Index: 205

Text #19

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2329. Min Act: -0.0001

Data Index: 585812 (C4 (Web Text))

Max Activating Token Index: 228