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

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

Neuron 629 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.9931. Min Act: -0.0001

Data Index: 137806 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.8894. Min Act: -0.0001

Data Index: 1338989 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.7995. Min Act: -0.0001

Data Index: 1319187 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.7384. Min Act: -0.0001

Data Index: 288189 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.7277. Min Act: -0.0001

Data Index: 376184 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.7253. Min Act: -0.0001

Data Index: 343581 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.6927. Min Act: -0.0001

Data Index: 321507 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.6490. Min Act: -0.0001

Data Index: 433449 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.6917. Min Act: -0.0001

Data Index: 448279 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.6789. Min Act: -0.0001

Data Index: 947452 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.7224. Min Act: -0.0001

Data Index: 945881 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.5760. Min Act: -0.0001

Data Index: 256619 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.5873. Min Act: -0.0001

Data Index: 265276 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.6239. Min Act: -0.0001

Data Index: 1011049 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.6332. Min Act: -0.0001

Data Index: 870712 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.6416. Min Act: -0.0001

Data Index: 975402 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.5765. Min Act: -0.0001

Data Index: 811876 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.5849. Min Act: -0.0001

Data Index: 464092 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.5914. Min Act: -0.0001

Data Index: 1023051 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.5662. Min Act: -0.0001

Data Index: 46397 (C4 (Web Text))

Max Activating Token Index: 444