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

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

Neuron 699 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1915. Min Act: -0.0000

Data Index: 436079 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1548. Min Act: -0.0001

Data Index: 772897 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1497. Min Act: -0.0001

Data Index: 759380 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1404. Min Act: -0.0001

Data Index: 229296 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1432. Min Act: -0.0001

Data Index: 1037568 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1295. Min Act: -0.0001

Data Index: 1103358 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1361. Min Act: -0.0001

Data Index: 1344434 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1174. Min Act: -0.0001

Data Index: 1071083 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1255. Min Act: -0.0001

Data Index: 110514 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1092. Min Act: -0.0001

Data Index: 945195 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1314. Min Act: -0.0001

Data Index: 924512 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1294. Min Act: -0.0001

Data Index: 494101 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1238. Min Act: -0.0001

Data Index: 19660 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1215. Min Act: -0.0001

Data Index: 1555797 (Python Code)

Max Activating Token Index: 612

Text #14

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.0987. Min Act: -0.0001

Data Index: 418482 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1085. Min Act: -0.0001

Data Index: 626281 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1007. Min Act: -0.0001

Data Index: 1147156 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1118. Min Act: -0.0001

Data Index: 1078556 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1617266 (Python Code)

Max Activating Token Index: 552

Text #19

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1189. Min Act: -0.0001

Data Index: 519051 (C4 (Web Text))

Max Activating Token Index: 161