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

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

Neuron 266 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.3172. Min Act: -0.0001

Data Index: 219462 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.3142. Min Act: -0.0001

Data Index: 1124545 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.2714. Min Act: -0.0001

Data Index: 600126 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.2480. Min Act: -0.0001

Data Index: 1063643 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.2874. Min Act: -0.0001

Data Index: 460838 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.2421. Min Act: -0.0001

Data Index: 1133835 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.2257. Min Act: -0.0001

Data Index: 739512 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.3403. Min Act: -0.0001

Data Index: 1211854 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.1362. Min Act: -0.0001

Data Index: 284950 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.1249. Min Act: -0.0001

Data Index: 1158091 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.1684. Min Act: -0.0001

Data Index: 781899 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.1264. Min Act: -0.0001

Data Index: 1063843 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.1194. Min Act: -0.0001

Data Index: 172233 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 1.3403. Min Range: -1.3403

Max Act: 0.9889. Min Act: -0.0001

Data Index: 243463 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.1733. Min Act: -0.0001

Data Index: 1240609 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.1327. Min Act: -0.0001

Data Index: 466005 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.0403. Min Act: -0.0001

Data Index: 771791 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.1355. Min Act: -0.0001

Data Index: 27643 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.0574. Min Act: -0.0001

Data Index: 1301764 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.0402. Min Act: -0.0001

Data Index: 216201 (C4 (Web Text))

Max Activating Token Index: 854