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

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

Neuron 3732 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0507. Min Act: -0.0001

Data Index: 626415 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0497. Min Act: -0.0001

Data Index: 68047 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0464. Min Act: -0.0001

Data Index: 641945 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0413. Min Act: -0.0001

Data Index: 220305 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0396. Min Act: -0.0001

Data Index: 627881 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0319. Min Act: -0.0001

Data Index: 176979 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0354. Min Act: -0.0001

Data Index: 1282633 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0358. Min Act: -0.0001

Data Index: 724486 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0347. Min Act: -0.0001

Data Index: 768023 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0334. Min Act: -0.0001

Data Index: 706259 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0341. Min Act: -0.0001

Data Index: 101798 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1040954 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0344. Min Act: -0.0001

Data Index: 992612 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0299. Min Act: -0.0001

Data Index: 652979 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1006407 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0318. Min Act: -0.0001

Data Index: 727199 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0314. Min Act: -0.0001

Data Index: 298156 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0292. Min Act: -0.0001

Data Index: 97673 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0302. Min Act: -0.0001

Data Index: 1054405 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0311. Min Act: -0.0001

Data Index: 803509 (C4 (Web Text))

Max Activating Token Index: 172