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

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

Neuron 192 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1680. Min Act: -0.0001

Data Index: 1135362 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1535. Min Act: -0.0001

Data Index: 1113687 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1445. Min Act: -0.0001

Data Index: 501236 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1410. Min Act: -0.0001

Data Index: 1014247 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1490. Min Act: -0.0001

Data Index: 905091 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1315. Min Act: -0.0001

Data Index: 323503 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1275. Min Act: -0.0001

Data Index: 161324 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1329. Min Act: -0.0001

Data Index: 61168 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1309. Min Act: -0.0001

Data Index: 169567 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1313. Min Act: -0.0001

Data Index: 1188952 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1307. Min Act: -0.0001

Data Index: 40259 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1156891 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1311. Min Act: -0.0001

Data Index: 426282 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1348. Min Act: -0.0001

Data Index: 517625 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1102. Min Act: -0.0001

Data Index: 45214 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1272129 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1148. Min Act: -0.0001

Data Index: 456214 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1232. Min Act: -0.0001

Data Index: 1279875 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1274. Min Act: -0.0001

Data Index: 258402 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1219. Min Act: -0.0001

Data Index: 22030 (C4 (Web Text))

Max Activating Token Index: 366