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

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

Neuron 4681 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: 0.3647. Min Range: -0.3647

Max Act: 0.3647. Min Act: -0.0001

Data Index: 1065500 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2669. Min Act: -0.0001

Data Index: 924313 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2582. Min Act: -0.0001

Data Index: 957371 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2435. Min Act: -0.0001

Data Index: 144045 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2386. Min Act: -0.0001

Data Index: 1332039 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2349. Min Act: -0.0001

Data Index: 356641 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2269. Min Act: -0.0001

Data Index: 17714 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2252. Min Act: -0.0001

Data Index: 561722 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2287. Min Act: -0.0001

Data Index: 181510 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2274. Min Act: -0.0001

Data Index: 763079 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2229. Min Act: -0.0001

Data Index: 825595 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2210. Min Act: -0.0001

Data Index: 1253998 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2288. Min Act: -0.0001

Data Index: 1294778 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2181. Min Act: -0.0001

Data Index: 1020312 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2171. Min Act: -0.0001

Data Index: 57649 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2185. Min Act: -0.0001

Data Index: 1035504 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2153. Min Act: -0.0001

Data Index: 634141 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2165. Min Act: -0.0001

Data Index: 520309 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2117. Min Act: -0.0001

Data Index: 254231 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2112. Min Act: -0.0001

Data Index: 1271631 (C4 (Web Text))

Max Activating Token Index: 34