Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2530 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0319. Min Act: -0.0001

Data Index: 1422976 (Python Code)

Max Activating Token Index: 882

Text #1

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0227. Min Act: -0.0001

Data Index: 564327 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0198. Min Act: -0.0001

Data Index: 645910 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0187. Min Act: -0.0001

Data Index: 237539 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0177. Min Act: -0.0001

Data Index: 502464 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0179. Min Act: -0.0001

Data Index: 536512 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0184. Min Act: -0.0001

Data Index: 730529 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0187. Min Act: -0.0001

Data Index: 1346172 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0186. Min Act: -0.0001

Data Index: 1266601 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0185. Min Act: -0.0001

Data Index: 1119381 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0169. Min Act: -0.0001

Data Index: 151741 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0182. Min Act: -0.0001

Data Index: 1602855 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1362297 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0174. Min Act: -0.0001

Data Index: 163462 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0167. Min Act: -0.0001

Data Index: 902466 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0171. Min Act: -0.0001

Data Index: 934287 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0169. Min Act: -0.0001

Data Index: 235183 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0171. Min Act: -0.0001

Data Index: 972610 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0175. Min Act: -0.0001

Data Index: 306870 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0164. Min Act: -0.0001

Data Index: 1478359 (Python Code)

Max Activating Token Index: 1023