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

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

Neuron 121 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.2928. Min Act: -0.0000

Data Index: 747002 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.3199. Min Act: -0.0000

Data Index: 70388 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.2512. Min Act: -0.0000

Data Index: 202125 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.2406. Min Act: -0.0000

Data Index: 924971 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.2519. Min Act: -0.0000

Data Index: 992647 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1042564 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.2192. Min Act: -0.0000

Data Index: 1172742 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.1809. Min Act: -0.0000

Data Index: 417310 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.1519. Min Act: -0.0000

Data Index: 1009649 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1273253 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.1656. Min Act: -0.0000

Data Index: 675662 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.1628. Min Act: -0.0000

Data Index: 497236 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.1472. Min Act: -0.0000

Data Index: 687861 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.1536. Min Act: -0.0000

Data Index: 1117520 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.1489. Min Act: -0.0000

Data Index: 495712 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.1408. Min Act: -0.0000

Data Index: 885564 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1051576 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.1346. Min Act: -0.0000

Data Index: 894134 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1319667 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.3199. Min Range: -0.3199

Max Act: 0.1336. Min Act: -0.0000

Data Index: 592823 (C4 (Web Text))

Max Activating Token Index: 661