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

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

Neuron 238 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2859. Min Act: -0.0002

Data Index: 382714 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2439. Min Act: -0.0002

Data Index: 561594 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2398. Min Act: -0.0002

Data Index: 1141194 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2437. Min Act: -0.0002

Data Index: 1042030 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2346. Min Act: -0.0002

Data Index: 727538 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2362. Min Act: -0.0003

Data Index: 1125835 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2293. Min Act: -0.0002

Data Index: 1243696 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2229. Min Act: -0.0002

Data Index: 499469 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2178. Min Act: -0.0002

Data Index: 504232 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2197. Min Act: -0.0002

Data Index: 683489 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2182. Min Act: -0.0002

Data Index: 238347 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2176. Min Act: -0.0002

Data Index: 419439 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2139. Min Act: -0.0002

Data Index: 1302845 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2114. Min Act: -0.0003

Data Index: 1035144 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2098. Min Act: -0.0002

Data Index: 597651 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2092. Min Act: -0.0002

Data Index: 949181 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2107. Min Act: -0.0002

Data Index: 175400 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2155. Min Act: -0.0002

Data Index: 72997 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2093. Min Act: -0.0002

Data Index: 567863 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2041. Min Act: -0.0002

Data Index: 330449 (C4 (Web Text))

Max Activating Token Index: 600