Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1077 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1343. Min Range: -1.1343

Max Act: 1.1253. Min Act: -0.0000

Data Index: 888998 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 1.1343. Min Range: -1.1343

Max Act: 1.1343. Min Act: -0.0000

Data Index: 1325017 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 1.1343. Min Range: -1.1343

Max Act: 1.0313. Min Act: -0.0001

Data Index: 214914 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 1.1343. Min Range: -1.1343

Max Act: 1.0715. Min Act: -0.0000

Data Index: 398524 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 1.1343. Min Range: -1.1343

Max Act: 1.0257. Min Act: -0.0000

Data Index: 999437 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 1.1343. Min Range: -1.1343

Max Act: 1.0794. Min Act: -0.0001

Data Index: 1187435 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 1.1343. Min Range: -1.1343

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1230065 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 1.1343. Min Range: -1.1343

Max Act: 1.0078. Min Act: -0.0000

Data Index: 553889 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 1.1343. Min Range: -1.1343

Max Act: 1.0541. Min Act: -0.0001

Data Index: 1317263 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 1.1343. Min Range: -1.1343

Max Act: 0.9324. Min Act: -0.0000

Data Index: 681055 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 1.1343. Min Range: -1.1343

Max Act: 1.0306. Min Act: -0.0001

Data Index: 1146864 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 1.1343. Min Range: -1.1343

Max Act: 0.9549. Min Act: -0.0000

Data Index: 742911 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 1.1343. Min Range: -1.1343

Max Act: 0.9844. Min Act: -0.0001

Data Index: 808899 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 1.1343. Min Range: -1.1343

Max Act: 0.9184. Min Act: -0.0001

Data Index: 1204703 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 1.1343. Min Range: -1.1343

Max Act: 1.0089. Min Act: -0.0000

Data Index: 426506 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 1.1343. Min Range: -1.1343

Max Act: 1.0312. Min Act: -0.0000

Data Index: 258442 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 1.1343. Min Range: -1.1343

Max Act: 0.9455. Min Act: -0.0000

Data Index: 543801 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 1.1343. Min Range: -1.1343

Max Act: 0.9430. Min Act: -0.0001

Data Index: 327643 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 1.1343. Min Range: -1.1343

Max Act: 1.0219. Min Act: -0.0000

Data Index: 943324 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 1.1343. Min Range: -1.1343

Max Act: 0.9941. Min Act: -0.0001

Data Index: 494912 (C4 (Web Text))

Max Activating Token Index: 494