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

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

Neuron 3738 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: 1.4905. Min Range: -1.4905

Max Act: 1.4905. Min Act: -0.0001

Data Index: 548738 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.4218. Min Act: -0.0001

Data Index: 1076004 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.4246. Min Act: -0.0000

Data Index: 930075 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.2351. Min Act: -0.0001

Data Index: 193802 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.1908. Min Act: -0.0001

Data Index: 372398 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.2083. Min Act: -0.0000

Data Index: 208743 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.1371. Min Act: -0.0001

Data Index: 694238 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.2281. Min Act: -0.0001

Data Index: 389085 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.1482. Min Act: -0.0001

Data Index: 45500 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.1547. Min Act: -0.0000

Data Index: 262142 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.1250. Min Act: -0.0001

Data Index: 927935 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.2136. Min Act: -0.0001

Data Index: 1060143 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.1247. Min Act: -0.0001

Data Index: 1109737 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.1584. Min Act: -0.0001

Data Index: 1225260 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.2570. Min Act: -0.0000

Data Index: 1353158 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.1533. Min Act: -0.0001

Data Index: 73091 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.0786. Min Act: -0.0000

Data Index: 85764 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.1450. Min Act: -0.0001

Data Index: 183409 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.2794. Min Act: -0.0000

Data Index: 961396 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.0705. Min Act: -0.0001

Data Index: 691064 (C4 (Web Text))

Max Activating Token Index: 192