Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 64 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.4311. Min Act: -0.0001

Data Index: 582607 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3402. Min Act: -0.0001

Data Index: 231630 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3195. Min Act: -0.0001

Data Index: 571326 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3166. Min Act: -0.0001

Data Index: 1176562 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.2700. Min Act: -0.0001

Data Index: 10810 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3197. Min Act: -0.0001

Data Index: 1221341 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.2961. Min Act: -0.0001

Data Index: 716612 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.2545. Min Act: -0.0001

Data Index: 1099150 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.2579. Min Act: -0.0001

Data Index: 239751 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.2283. Min Act: -0.0001

Data Index: 822892 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.2555. Min Act: -0.0001

Data Index: 276779 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.2644. Min Act: -0.0001

Data Index: 373633 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.2405. Min Act: -0.0001

Data Index: 490590 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.2563. Min Act: -0.0001

Data Index: 269104 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.2213. Min Act: -0.0001

Data Index: 1186673 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.2454. Min Act: -0.0001

Data Index: 1336 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.2971. Min Act: -0.0001

Data Index: 1126646 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.2395. Min Act: -0.0001

Data Index: 1343615 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.2581. Min Act: -0.0001

Data Index: 1113262 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.2472. Min Act: -0.0001

Data Index: 244134 (C4 (Web Text))

Max Activating Token Index: 113