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

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

Neuron 4962 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.8933. Min Act: -0.0001

Data Index: 53149 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.8392. Min Act: -0.0001

Data Index: 687833 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.8863. Min Act: -0.0001

Data Index: 502307 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.8445. Min Act: -0.0001

Data Index: 678181 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.8601. Min Act: -0.0001

Data Index: 831569 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.6288. Min Act: -0.0001

Data Index: 709016 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.4188. Min Act: -0.0001

Data Index: 13292 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.4508. Min Act: -0.0001

Data Index: 1285222 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.4427. Min Act: -0.0001

Data Index: 492393 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.4161. Min Act: -0.0001

Data Index: 1331849 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.2979. Min Act: -0.0001

Data Index: 690793 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.1156. Min Act: -0.0001

Data Index: 491606 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.3517. Min Act: -0.0001

Data Index: 98087 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.3413. Min Act: -0.0001

Data Index: 908283 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.2129. Min Act: -0.0001

Data Index: 1071619 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.2339. Min Act: -0.0001

Data Index: 134150 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.1625. Min Act: -0.0001

Data Index: 597694 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.2241. Min Act: -0.0001

Data Index: 808076 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.2142. Min Act: -0.0001

Data Index: 1064350 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 1.8933. Min Range: -1.8933

Max Act: 1.1998. Min Act: -0.0001

Data Index: 894312 (C4 (Web Text))

Max Activating Token Index: 501