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

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

Neuron 4144 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1679. Min Act: -0.0002

Data Index: 919222 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1784. Min Act: -0.0002

Data Index: 940236 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1767. Min Act: -0.0002

Data Index: 218995 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1519. Min Act: -0.0002

Data Index: 557935 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1684. Min Act: -0.0002

Data Index: 437668 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1687. Min Act: -0.0002

Data Index: 231031 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1456. Min Act: -0.0002

Data Index: 301330 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1480. Min Act: -0.0002

Data Index: 1111417 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1436. Min Act: -0.0002

Data Index: 645649 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1309. Min Act: -0.0002

Data Index: 9778 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1456. Min Act: -0.0002

Data Index: 462134 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1480. Min Act: -0.0002

Data Index: 47126 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1365. Min Act: -0.0002

Data Index: 1163090 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1218. Min Act: -0.0002

Data Index: 1236881 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1352. Min Act: -0.0002

Data Index: 415553 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1371. Min Act: -0.0002

Data Index: 1139665 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1335. Min Act: -0.0002

Data Index: 448484 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1288. Min Act: -0.0002

Data Index: 1138136 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1268. Min Act: -0.0002

Data Index: 1099943 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1249. Min Act: -0.0002

Data Index: 491364 (C4 (Web Text))

Max Activating Token Index: 932