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

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

Neuron 3309 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2825. Min Range: -1.2825

Max Act: 1.2825. Min Act: -0.0001

Data Index: 1149254 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 1.2825. Min Range: -1.2825

Max Act: 1.2138. Min Act: -0.0001

Data Index: 728872 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 1.2825. Min Range: -1.2825

Max Act: 1.0748. Min Act: -0.0001

Data Index: 1174168 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.9823. Min Act: -0.0001

Data Index: 691469 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.9626. Min Act: -0.0001

Data Index: 1163531 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.9661. Min Act: -0.0001

Data Index: 1010899 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.9095. Min Act: -0.0001

Data Index: 880702 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.9424. Min Act: -0.0001

Data Index: 685123 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.9235. Min Act: -0.0001

Data Index: 561564 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.9021. Min Act: -0.0001

Data Index: 476040 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.9307. Min Act: -0.0001

Data Index: 428218 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8324. Min Act: -0.0001

Data Index: 1181339 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.9160. Min Act: -0.0001

Data Index: 1177609 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.9263. Min Act: -0.0001

Data Index: 656537 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8896. Min Act: -0.0001

Data Index: 1027583 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8657. Min Act: -0.0001

Data Index: 954358 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8568. Min Act: -0.0001

Data Index: 1010943 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8629. Min Act: -0.0001

Data Index: 653474 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8668. Min Act: -0.0001

Data Index: 897432 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8226. Min Act: -0.0001

Data Index: 1156420 (C4 (Web Text))

Max Activating Token Index: 510