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

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

Neuron 3986 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1591. Min Act: -0.0000

Data Index: 484815 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1540. Min Act: -0.0000

Data Index: 1284725 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1418. Min Act: -0.0000

Data Index: 416934 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1368. Min Act: -0.0000

Data Index: 786297 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1329. Min Act: -0.0000

Data Index: 559019 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1308. Min Act: -0.0000

Data Index: 506113 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1408. Min Act: -0.0000

Data Index: 937087 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1282. Min Act: -0.0000

Data Index: 1142903 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1319. Min Act: -0.0000

Data Index: 615293 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1255. Min Act: -0.0000

Data Index: 116470 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1312. Min Act: -0.0000

Data Index: 1299181 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1356. Min Act: -0.0000

Data Index: 1108671 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1226. Min Act: -0.0000

Data Index: 856004 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1255. Min Act: -0.0000

Data Index: 391273 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1285. Min Act: -0.0000

Data Index: 175281 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1425662 (Python Code)

Max Activating Token Index: 952

Text #16

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1178. Min Act: -0.0000

Data Index: 1171321 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1130. Min Act: -0.0000

Data Index: 1198956 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1258. Min Act: -0.0000

Data Index: 553586 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1109. Min Act: -0.0000

Data Index: 737001 (C4 (Web Text))

Max Activating Token Index: 97