Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3624 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.3068. Min Act: 0.0000

Data Index: 451350 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.3123. Min Act: 0.0000

Data Index: 509383 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.3004. Min Act: -0.0000

Data Index: 1411876 (Python Code)

Max Activating Token Index: 333

Text #3

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2894. Min Act: -0.0000

Data Index: 71551 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.3201. Min Act: -0.0000

Data Index: 39508 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2875. Min Act: -0.0000

Data Index: 453493 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2859. Min Act: -0.0000

Data Index: 155626 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2726. Min Act: -0.0000

Data Index: 329685 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1022148 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2933. Min Act: -0.0000

Data Index: 530682 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2717. Min Act: -0.0000

Data Index: 810985 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2404. Min Act: -0.0000

Data Index: 60567 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2397. Min Act: -0.0000

Data Index: 238708 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2533. Min Act: -0.0000

Data Index: 853277 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2436. Min Act: -0.0001

Data Index: 1639227 (Python Code)

Max Activating Token Index: 698

Text #15

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2424. Min Act: 0.0000

Data Index: 494608 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2419. Min Act: -0.0000

Data Index: 1154828 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2267. Min Act: -0.0000

Data Index: 820591 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2313. Min Act: -0.0000

Data Index: 941684 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2365. Min Act: 0.0000

Data Index: 352409 (C4 (Web Text))

Max Activating Token Index: 145