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

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

Neuron 3868 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2887. Min Act: -0.0000

Data Index: 1094309 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2419. Min Act: -0.0000

Data Index: 1160422 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2285. Min Act: -0.0000

Data Index: 937334 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2164. Min Act: -0.0000

Data Index: 826888 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2311. Min Act: -0.0000

Data Index: 28529 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2091. Min Act: -0.0000

Data Index: 471649 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.1949. Min Act: -0.0000

Data Index: 1298474 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.1932. Min Act: -0.0000

Data Index: 698864 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.1982. Min Act: -0.0000

Data Index: 41655 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.1834. Min Act: -0.0000

Data Index: 1358246 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.1766. Min Act: -0.0000

Data Index: 107297 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2019. Min Act: -0.0000

Data Index: 565003 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.1882. Min Act: -0.0000

Data Index: 487259 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.1907. Min Act: -0.0000

Data Index: 1008985 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.1705. Min Act: -0.0000

Data Index: 41905 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.1657. Min Act: -0.0000

Data Index: 262819 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.1701. Min Act: -0.0000

Data Index: 174381 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.1708. Min Act: -0.0000

Data Index: 1266601 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1153378 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.1757. Min Act: -0.0000

Data Index: 525004 (C4 (Web Text))

Max Activating Token Index: 743