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

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

Neuron 934 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.8110. Min Act: -0.0001

Data Index: 725241 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.6773. Min Act: -0.0001

Data Index: 564284 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.6172. Min Act: -0.0001

Data Index: 188248 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.5520. Min Act: -0.0001

Data Index: 932376 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.4585. Min Act: -0.0001

Data Index: 685581 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.3385. Min Act: -0.0001

Data Index: 486119 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.4473. Min Act: -0.0001

Data Index: 1020700 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.2547. Min Act: -0.0001

Data Index: 1094020 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.3413. Min Act: -0.0001

Data Index: 85552 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.2628. Min Act: -0.0001

Data Index: 173990 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.2145. Min Act: -0.0001

Data Index: 733894 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.2866. Min Act: -0.0001

Data Index: 859174 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.2281. Min Act: -0.0001

Data Index: 1215934 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.1890. Min Act: -0.0001

Data Index: 1327225 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.1788. Min Act: -0.0001

Data Index: 1065788 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.1756. Min Act: -0.0001

Data Index: 1292542 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.2055. Min Act: -0.0001

Data Index: 1142435 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.1553. Min Act: -0.0001

Data Index: 298834 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.1870. Min Act: -0.0001

Data Index: 932550 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.0738. Min Act: -0.0001

Data Index: 896784 (C4 (Web Text))

Max Activating Token Index: 294