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

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

Neuron 3862 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4733. Min Act: -0.0001

Data Index: 1040392 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4257. Min Act: -0.0001

Data Index: 986575 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4308. Min Act: -0.0001

Data Index: 1085542 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3724. Min Act: -0.0001

Data Index: 98489 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3638. Min Act: -0.0001

Data Index: 282091 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3693. Min Act: -0.0001

Data Index: 87391 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3694. Min Act: -0.0002

Data Index: 1077455 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3429. Min Act: -0.0001

Data Index: 703527 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3375. Min Act: -0.0001

Data Index: 357197 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3599. Min Act: -0.0002

Data Index: 498157 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3703. Min Act: -0.0002

Data Index: 669926 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3494. Min Act: -0.0001

Data Index: 720014 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3714. Min Act: -0.0001

Data Index: 1641864 (Python Code)

Max Activating Token Index: 759

Text #13

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3328. Min Act: -0.0002

Data Index: 546653 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3499. Min Act: -0.0001

Data Index: 882088 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3371. Min Act: -0.0002

Data Index: 506158 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3261. Min Act: -0.0001

Data Index: 1250466 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3743. Min Act: -0.0002

Data Index: 481828 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3156. Min Act: -0.0001

Data Index: 341928 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3446. Min Act: -0.0001

Data Index: 678062 (C4 (Web Text))

Max Activating Token Index: 938