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

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

Neuron 4898 in Layer 0

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: 0.0258. Min Range: -0.0258

Max Act: 0.0258. Min Act: -0.0001

Data Index: 723923 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0257. Min Act: -0.0001

Data Index: 171530 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0237. Min Act: -0.0001

Data Index: 533728 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0236. Min Act: -0.0002

Data Index: 1570224 (Python Code)

Max Activating Token Index: 171

Text #4

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0226. Min Act: -0.0001

Data Index: 938887 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0224. Min Act: -0.0001

Data Index: 1181100 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0225. Min Act: -0.0001

Data Index: 660844 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0225. Min Act: -0.0001

Data Index: 574576 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0221. Min Act: -0.0001

Data Index: 920247 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1013789 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0220. Min Act: -0.0001

Data Index: 431141 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0220. Min Act: -0.0001

Data Index: 936500 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0219. Min Act: -0.0001

Data Index: 205074 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0222. Min Act: -0.0001

Data Index: 150426 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0222. Min Act: -0.0001

Data Index: 763294 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0218. Min Act: -0.0001

Data Index: 727565 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0218. Min Act: -0.0001

Data Index: 1593793 (Python Code)

Max Activating Token Index: 8

Text #17

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1476559 (Python Code)

Max Activating Token Index: 20

Text #18

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0218. Min Act: -0.0001

Data Index: 1404752 (Python Code)

Max Activating Token Index: 923

Text #19

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0220. Min Act: -0.0001

Data Index: 45975 (C4 (Web Text))

Max Activating Token Index: 246