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

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

Neuron 257 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.7046. Min Act: -0.0002

Data Index: 1119198 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.6394. Min Act: -0.0002

Data Index: 383588 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.6208. Min Act: -0.0002

Data Index: 226419 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.6454. Min Act: -0.0002

Data Index: 774826 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.6430. Min Act: -0.0002

Data Index: 226842 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.6224. Min Act: -0.0002

Data Index: 958440 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.5937. Min Act: -0.0002

Data Index: 1332005 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.6336. Min Act: -0.0002

Data Index: 341445 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.5597. Min Act: -0.0002

Data Index: 992774 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.6226. Min Act: -0.0002

Data Index: 1058142 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.6216. Min Act: -0.0002

Data Index: 358869 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.6004. Min Act: -0.0002

Data Index: 1105154 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.6179. Min Act: -0.0002

Data Index: 1168945 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.5829. Min Act: -0.0002

Data Index: 1076270 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.5973. Min Act: -0.0002

Data Index: 337225 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.6328. Min Act: -0.0002

Data Index: 29889 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.6141. Min Act: -0.0002

Data Index: 879784 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.6291. Min Act: -0.0002

Data Index: 843667 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.6135. Min Act: -0.0002

Data Index: 728901 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.7046. Min Range: -0.7046

Max Act: 0.6275. Min Act: -0.0001

Data Index: 624483 (C4 (Web Text))

Max Activating Token Index: 396