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

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

Neuron 1874 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: 0.1301. Min Range: -0.1301

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1039061 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1149. Min Act: -0.0001

Data Index: 475384 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1248. Min Act: -0.0001

Data Index: 28667 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1147. Min Act: -0.0001

Data Index: 333910 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1301. Min Act: -0.0001

Data Index: 1332540 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1237. Min Act: -0.0001

Data Index: 1140243 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1242. Min Act: -0.0001

Data Index: 952500 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1259. Min Act: -0.0001

Data Index: 126644 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1201. Min Act: -0.0001

Data Index: 89658 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1129001 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1228877 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1252. Min Act: -0.0001

Data Index: 635358 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1094. Min Act: -0.0001

Data Index: 400140 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1185. Min Act: -0.0001

Data Index: 293440 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1207. Min Act: -0.0001

Data Index: 756770 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1137. Min Act: -0.0001

Data Index: 170782 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1221. Min Act: -0.0001

Data Index: 993882 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1217. Min Act: -0.0001

Data Index: 711161 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1137. Min Act: -0.0001

Data Index: 200918 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1170. Min Act: -0.0001

Data Index: 449836 (C4 (Web Text))

Max Activating Token Index: 478