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

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

Neuron 3081 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: 0.1868. Min Range: -0.1868

Max Act: 0.1868. Min Act: -0.0001

Data Index: 988841 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1854. Min Act: -0.0001

Data Index: 884805 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1823. Min Act: -0.0001

Data Index: 457302 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1622. Min Act: -0.0001

Data Index: 754728 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1547. Min Act: -0.0001

Data Index: 6158 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1472. Min Act: -0.0001

Data Index: 519241 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1457. Min Act: -0.0001

Data Index: 199399 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1371. Min Act: -0.0001

Data Index: 289556 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1418. Min Act: -0.0001

Data Index: 312406 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1244. Min Act: -0.0001

Data Index: 352023 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1462. Min Act: -0.0001

Data Index: 949691 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1307. Min Act: -0.0001

Data Index: 1172579 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1382. Min Act: -0.0001

Data Index: 1211765 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1437. Min Act: -0.0001

Data Index: 835631 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1272. Min Act: -0.0001

Data Index: 668051 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1258732 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1313. Min Act: -0.0001

Data Index: 417749 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1313. Min Act: -0.0001

Data Index: 156842 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1299. Min Act: -0.0001

Data Index: 488781 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1285. Min Act: -0.0001

Data Index: 878767 (C4 (Web Text))

Max Activating Token Index: 836