Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2683 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4210. Min Range: -2.4210

Max Act: 2.4210. Min Act: -0.0000

Data Index: 1165497 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.8118. Min Act: -0.0000

Data Index: 624276 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.7768. Min Act: -0.0000

Data Index: 745603 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.6678. Min Act: -0.0000

Data Index: 1152627 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.4183. Min Act: -0.0000

Data Index: 177252 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.3682. Min Act: -0.0000

Data Index: 642655 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.5741. Min Act: -0.0000

Data Index: 478645 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.3771. Min Act: -0.0000

Data Index: 114323 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.6983. Min Act: -0.0000

Data Index: 120721 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.6085. Min Act: -0.0000

Data Index: 522852 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.4041. Min Act: -0.0000

Data Index: 969697 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.2216. Min Act: -0.0000

Data Index: 696466 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.1663. Min Act: -0.0000

Data Index: 990031 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.3563. Min Act: -0.0000

Data Index: 1223289 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.1626. Min Act: -0.0000

Data Index: 1239939 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.2283. Min Act: -0.0000

Data Index: 1099704 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.2900. Min Act: -0.0000

Data Index: 815083 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.2116. Min Act: -0.0000

Data Index: 485216 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.1132. Min Act: -0.0000

Data Index: 978955 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.0541. Min Act: -0.0000

Data Index: 550150 (C4 (Web Text))

Max Activating Token Index: 447