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

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

Neuron 275 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2530. Min Act: -0.0001

Data Index: 783926 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2377. Min Act: -0.0001

Data Index: 510849 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2447. Min Act: -0.0001

Data Index: 804795 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2236. Min Act: -0.0001

Data Index: 353975 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2242. Min Act: -0.0001

Data Index: 141953 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2205. Min Act: -0.0001

Data Index: 1021299 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2201. Min Act: -0.0001

Data Index: 143519 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2193. Min Act: -0.0001

Data Index: 1096280 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2192. Min Act: -0.0001

Data Index: 734864 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2274. Min Act: -0.0001

Data Index: 114870 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2262. Min Act: -0.0001

Data Index: 159225 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1003633 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2064. Min Act: -0.0001

Data Index: 1161077 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1974. Min Act: -0.0001

Data Index: 979656 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2204. Min Act: -0.0000

Data Index: 722319 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2118. Min Act: -0.0001

Data Index: 391709 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2109. Min Act: -0.0001

Data Index: 957397 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2106. Min Act: -0.0001

Data Index: 773108 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2114. Min Act: -0.0001

Data Index: 463738 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2096. Min Act: -0.0001

Data Index: 354024 (C4 (Web Text))

Max Activating Token Index: 903