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

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

Neuron 3105 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: 1.7920. Min Range: -1.7920

Max Act: 1.7920. Min Act: -0.0001

Data Index: 904835 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 1.7920. Min Range: -1.7920

Max Act: 1.7177. Min Act: -0.0001

Data Index: 543668 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 1.7920. Min Range: -1.7920

Max Act: 1.5189. Min Act: -0.0001

Data Index: 109198 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 1.7920. Min Range: -1.7920

Max Act: 1.5071. Min Act: -0.0001

Data Index: 663693 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 1.7920. Min Range: -1.7920

Max Act: 1.7509. Min Act: -0.0001

Data Index: 1291445 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 1.7920. Min Range: -1.7920

Max Act: 1.3433. Min Act: -0.0001

Data Index: 1103549 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 1.7920. Min Range: -1.7920

Max Act: 1.4913. Min Act: -0.0001

Data Index: 323408 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 1.7920. Min Range: -1.7920

Max Act: 1.3165. Min Act: -0.0001

Data Index: 69834 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 1.7920. Min Range: -1.7920

Max Act: 1.3748. Min Act: -0.0001

Data Index: 197340 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 1.7920. Min Range: -1.7920

Max Act: 1.3598. Min Act: -0.0001

Data Index: 665560 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 1.7920. Min Range: -1.7920

Max Act: 1.3927. Min Act: -0.0001

Data Index: 972652 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 1.7920. Min Range: -1.7920

Max Act: 1.3031. Min Act: -0.0001

Data Index: 481677 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 1.7920. Min Range: -1.7920

Max Act: 1.3405. Min Act: -0.0001

Data Index: 128402 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 1.7920. Min Range: -1.7920

Max Act: 1.3248. Min Act: -0.0001

Data Index: 700135 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 1.7920. Min Range: -1.7920

Max Act: 1.3092. Min Act: -0.0001

Data Index: 1275712 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 1.7920. Min Range: -1.7920

Max Act: 1.3423. Min Act: -0.0001

Data Index: 229796 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 1.7920. Min Range: -1.7920

Max Act: 1.2633. Min Act: -0.0001

Data Index: 1282115 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 1.7920. Min Range: -1.7920

Max Act: 1.2569. Min Act: -0.0001

Data Index: 1338178 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 1.7920. Min Range: -1.7920

Max Act: 1.2575. Min Act: -0.0001

Data Index: 26085 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 1.7920. Min Range: -1.7920

Max Act: 1.3340. Min Act: -0.0001

Data Index: 1121548 (C4 (Web Text))

Max Activating Token Index: 928