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

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

Neuron 954 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: 0.7823. Min Range: -0.7823

Max Act: 0.7823. Min Act: -0.0001

Data Index: 295085 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.6778. Min Act: -0.0001

Data Index: 952765 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.7028. Min Act: -0.0001

Data Index: 1232929 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.6151. Min Act: -0.0001

Data Index: 758437 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.6397. Min Act: -0.0001

Data Index: 577491 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5777. Min Act: -0.0001

Data Index: 454573 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.6372. Min Act: -0.0001

Data Index: 978127 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.6019. Min Act: -0.0001

Data Index: 221439 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5871. Min Act: -0.0001

Data Index: 516547 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5698. Min Act: -0.0001

Data Index: 24554 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5493. Min Act: -0.0001

Data Index: 696941 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5778. Min Act: -0.0001

Data Index: 1293300 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5383. Min Act: -0.0001

Data Index: 108765 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5574. Min Act: -0.0001

Data Index: 390658 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5316. Min Act: -0.0001

Data Index: 639554 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5683. Min Act: -0.0001

Data Index: 1103886 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5435. Min Act: -0.0001

Data Index: 981898 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5604. Min Act: -0.0001

Data Index: 257879 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5396. Min Act: -0.0001

Data Index: 859157 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.4415. Min Act: -0.0001

Data Index: 207843 (C4 (Web Text))

Max Activating Token Index: 550