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

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

Neuron 2540 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: 0.0255. Min Range: -0.0255

Max Act: 0.0255. Min Act: -0.0001

Data Index: 67535 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0252. Min Act: -0.0001

Data Index: 218198 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0254. Min Act: -0.0001

Data Index: 1078787 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0254. Min Act: -0.0001

Data Index: 211617 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0251. Min Act: -0.0001

Data Index: 335064 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0249. Min Act: -0.0002

Data Index: 570881 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0251. Min Act: -0.0001

Data Index: 1250299 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0243. Min Act: -0.0001

Data Index: 837186 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0241. Min Act: -0.0001

Data Index: 594121 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0242. Min Act: -0.0001

Data Index: 844773 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0241. Min Act: -0.0001

Data Index: 1086773 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0240. Min Act: -0.0001

Data Index: 1259636 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0230. Min Act: -0.0001

Data Index: 7091 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0229. Min Act: -0.0001

Data Index: 480124 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0229. Min Act: -0.0001

Data Index: 410190 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0228. Min Act: -0.0001

Data Index: 126658 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0227. Min Act: -0.0001

Data Index: 197486 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0225. Min Act: -0.0001

Data Index: 18805 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0224. Min Act: -0.0001

Data Index: 895395 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0223. Min Act: -0.0001

Data Index: 990324 (C4 (Web Text))

Max Activating Token Index: 663