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

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

Neuron 3887 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1802. Min Range: -1.1802

Max Act: 1.1802. Min Act: -0.0000

Data Index: 146391 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 1.1802. Min Range: -1.1802

Max Act: 1.1194. Min Act: -0.0000

Data Index: 343876 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.8924. Min Act: -0.0000

Data Index: 1174053 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.8675. Min Act: -0.0000

Data Index: 842381 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 1.1802. Min Range: -1.1802

Max Act: 1.0736. Min Act: -0.0000

Data Index: 634031 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.7849. Min Act: -0.0000

Data Index: 559587 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1253202 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.8081. Min Act: -0.0000

Data Index: 353483 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.7735. Min Act: -0.0000

Data Index: 914066 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.7246. Min Act: -0.0000

Data Index: 518463 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.7461. Min Act: -0.0000

Data Index: 504666 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.7036. Min Act: -0.0000

Data Index: 493224 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.6942. Min Act: -0.0000

Data Index: 791943 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.6753. Min Act: -0.0000

Data Index: 1207974 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1003810 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.6986. Min Act: -0.0000

Data Index: 194531 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.6227. Min Act: -0.0000

Data Index: 801069 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.6272. Min Act: -0.0000

Data Index: 19830 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.6645. Min Act: -0.0000

Data Index: 224329 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.6572. Min Act: -0.0000

Data Index: 146548 (C4 (Web Text))

Max Activating Token Index: 317