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

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

Neuron 4782 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0520. Min Act: -0.0002

Data Index: 118054 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0511. Min Act: -0.0002

Data Index: 877430 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0489. Min Act: -0.0002

Data Index: 817797 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0472. Min Act: -0.0002

Data Index: 842631 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1284323 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0463. Min Act: -0.0002

Data Index: 780308 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0461. Min Act: -0.0002

Data Index: 343690 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0442. Min Act: -0.0002

Data Index: 967733 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0458. Min Act: -0.0002

Data Index: 643892 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1082173 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0421. Min Act: -0.0002

Data Index: 750940 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0422. Min Act: -0.0002

Data Index: 41374 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1329387 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0411. Min Act: -0.0002

Data Index: 910662 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0395. Min Act: -0.0002

Data Index: 461290 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0400. Min Act: -0.0002

Data Index: 462413 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0400. Min Act: -0.0002

Data Index: 556024 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0399. Min Act: -0.0002

Data Index: 157129 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0384. Min Act: -0.0002

Data Index: 908056 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0383. Min Act: -0.0002

Data Index: 48401 (C4 (Web Text))

Max Activating Token Index: 699