Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 672 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1446. Min Act: -0.0002

Data Index: 880478 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1285. Min Act: -0.0002

Data Index: 270056 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1263. Min Act: -0.0002

Data Index: 321854 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1250. Min Act: -0.0002

Data Index: 394418 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1291. Min Act: -0.0001

Data Index: 549768 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1275. Min Act: -0.0002

Data Index: 1031033 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1272. Min Act: -0.0002

Data Index: 161249 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1219. Min Act: -0.0002

Data Index: 913016 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1237. Min Act: -0.0002

Data Index: 137823 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1291. Min Act: -0.0001

Data Index: 1022813 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1088. Min Act: -0.0001

Data Index: 336956 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1175. Min Act: -0.0001

Data Index: 440286 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1199. Min Act: -0.0002

Data Index: 845057 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1239. Min Act: -0.0002

Data Index: 677909 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1027. Min Act: -0.0002

Data Index: 632924 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1107. Min Act: -0.0002

Data Index: 109887 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1182. Min Act: -0.0002

Data Index: 419933 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1232. Min Act: -0.0001

Data Index: 536526 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1185. Min Act: -0.0002

Data Index: 1351326 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1263. Min Act: -0.0002

Data Index: 889298 (C4 (Web Text))

Max Activating Token Index: 564