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

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

Neuron 4508 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.4324. Min Act: -0.0000

Data Index: 585571 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3937. Min Act: -0.0000

Data Index: 1234688 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3569. Min Act: -0.0000

Data Index: 779905 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3436. Min Act: -0.0000

Data Index: 705764 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3440. Min Act: -0.0000

Data Index: 636025 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3314. Min Act: -0.0000

Data Index: 691827 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3242. Min Act: -0.0000

Data Index: 569953 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3243. Min Act: -0.0000

Data Index: 546957 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1157544 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1163962 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2954. Min Act: -0.0000

Data Index: 716515 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3024. Min Act: -0.0000

Data Index: 562102 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2900. Min Act: -0.0000

Data Index: 907017 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2901. Min Act: -0.0000

Data Index: 1311875 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2895. Min Act: -0.0000

Data Index: 400804 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2801. Min Act: -0.0000

Data Index: 1326183 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2773. Min Act: -0.0000

Data Index: 788099 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2849. Min Act: -0.0000

Data Index: 202994 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2929. Min Act: -0.0000

Data Index: 191423 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2770. Min Act: -0.0000

Data Index: 1115567 (C4 (Web Text))

Max Activating Token Index: 602