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

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

Neuron 896 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: 0.1841. Min Range: -0.1841

Max Act: 0.1841. Min Act: -0.0001

Data Index: 1320126 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1679. Min Act: -0.0001

Data Index: 441400 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1555. Min Act: -0.0001

Data Index: 1482977 (Python Code)

Max Activating Token Index: 221

Text #3

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1523. Min Act: -0.0001

Data Index: 434663 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1470. Min Act: -0.0001

Data Index: 821890 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1430. Min Act: -0.0001

Data Index: 834603 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1439. Min Act: -0.0001

Data Index: 548195 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1465. Min Act: -0.0001

Data Index: 682601 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1397. Min Act: -0.0001

Data Index: 953253 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1383. Min Act: -0.0001

Data Index: 1499809 (Python Code)

Max Activating Token Index: 622

Text #10

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1321. Min Act: -0.0001

Data Index: 511129 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1334. Min Act: -0.0001

Data Index: 900102 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1368. Min Act: -0.0001

Data Index: 372050 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1359. Min Act: -0.0001

Data Index: 1051863 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1343. Min Act: -0.0001

Data Index: 250614 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1249. Min Act: -0.0001

Data Index: 1179842 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1278. Min Act: -0.0001

Data Index: 644032 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1271. Min Act: -0.0001

Data Index: 470235 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1318. Min Act: -0.0001

Data Index: 915962 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1229. Min Act: -0.0001

Data Index: 1335175 (C4 (Web Text))

Max Activating Token Index: 384