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

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

Neuron 1877 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: 0.5029. Min Range: -0.5029

Max Act: 0.5029. Min Act: -0.0000

Data Index: 977313 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.2781. Min Act: -0.0001

Data Index: 961999 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.2851. Min Act: -0.0001

Data Index: 167103 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.2506. Min Act: -0.0001

Data Index: 361476 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.2209. Min Act: -0.0001

Data Index: 1050275 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1255900 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.2267. Min Act: -0.0001

Data Index: 178193 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.2156. Min Act: -0.0001

Data Index: 1038205 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.2436. Min Act: -0.0000

Data Index: 151346 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.2189. Min Act: -0.0001

Data Index: 600980 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.2108. Min Act: -0.0001

Data Index: 1031414 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.2162. Min Act: -0.0001

Data Index: 766315 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.2152. Min Act: -0.0001

Data Index: 365022 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.2004. Min Act: -0.0001

Data Index: 641239 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.2066. Min Act: -0.0001

Data Index: 797369 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.2119. Min Act: -0.0001

Data Index: 905565 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.2187. Min Act: -0.0001

Data Index: 853158 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.2034. Min Act: -0.0000

Data Index: 949683 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.2034. Min Act: -0.0001

Data Index: 800298 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.5029. Min Range: -0.5029

Max Act: 0.1957. Min Act: -0.0001

Data Index: 81225 (C4 (Web Text))

Max Activating Token Index: 646