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

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

Neuron 2546 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.3894. Min Act: -0.0001

Data Index: 338004 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.3618. Min Act: -0.0000

Data Index: 661122 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.3225. Min Act: -0.0001

Data Index: 811026 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4713. Min Act: -0.0001

Data Index: 108740 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4584. Min Act: -0.0001

Data Index: 432171 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4497. Min Act: -0.0001

Data Index: 450075 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.2719. Min Act: -0.0001

Data Index: 337567 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.3250. Min Act: -0.0000

Data Index: 1288558 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.2208. Min Act: -0.0001

Data Index: 1357745 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.3366. Min Act: -0.0000

Data Index: 720851 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.2359. Min Act: -0.0001

Data Index: 799962 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.2487. Min Act: -0.0000

Data Index: 319393 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.2389. Min Act: -0.0000

Data Index: 1303021 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.1557. Min Act: -0.0001

Data Index: 799326 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.2136. Min Act: -0.0000

Data Index: 797096 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.1722. Min Act: -0.0000

Data Index: 345142 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.1647. Min Act: -0.0000

Data Index: 1335084 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.3437. Min Act: -0.0000

Data Index: 1197801 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.0626. Min Act: -0.0000

Data Index: 780989 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.2549. Min Act: -0.0000

Data Index: 629818 (C4 (Web Text))

Max Activating Token Index: 198