Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4626 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0784. Min Range: -3.0784

Max Act: 3.0784. Min Act: -0.0000

Data Index: 660934 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 3.0784. Min Range: -3.0784

Max Act: 2.7200. Min Act: -0.0000

Data Index: 9305 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 3.0784. Min Range: -3.0784

Max Act: 2.4929. Min Act: -0.0000

Data Index: 632165 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 3.0784. Min Range: -3.0784

Max Act: 2.2092. Min Act: -0.0000

Data Index: 44324 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 3.0784. Min Range: -3.0784

Max Act: 2.1371. Min Act: -0.0000

Data Index: 1031586 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 3.0784. Min Range: -3.0784

Max Act: 2.0008. Min Act: -0.0000

Data Index: 251148 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 3.0784. Min Range: -3.0784

Max Act: 1.9684. Min Act: -0.0000

Data Index: 1352652 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 3.0784. Min Range: -3.0784

Max Act: 2.1387. Min Act: -0.0000

Data Index: 300479 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 3.0784. Min Range: -3.0784

Max Act: 2.0198. Min Act: -0.0000

Data Index: 1299470 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 3.0784. Min Range: -3.0784

Max Act: 1.9972. Min Act: -0.0000

Data Index: 209664 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 3.0784. Min Range: -3.0784

Max Act: 1.7805. Min Act: -0.0000

Data Index: 9243 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 3.0784. Min Range: -3.0784

Max Act: 1.9515. Min Act: -0.0000

Data Index: 980016 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 3.0784. Min Range: -3.0784

Max Act: 1.8420. Min Act: -0.0000

Data Index: 67369 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 3.0784. Min Range: -3.0784

Max Act: 1.9305. Min Act: -0.0000

Data Index: 507695 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 3.0784. Min Range: -3.0784

Max Act: 1.8372. Min Act: -0.0000

Data Index: 89479 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 3.0784. Min Range: -3.0784

Max Act: 2.0113. Min Act: -0.0000

Data Index: 642806 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 3.0784. Min Range: -3.0784

Max Act: 1.8170. Min Act: -0.0000

Data Index: 447407 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 3.0784. Min Range: -3.0784

Max Act: 1.8006. Min Act: -0.0000

Data Index: 1011101 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 3.0784. Min Range: -3.0784

Max Act: 1.8818. Min Act: -0.0000

Data Index: 258092 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 3.0784. Min Range: -3.0784

Max Act: 1.8276. Min Act: -0.0000

Data Index: 799195 (C4 (Web Text))

Max Activating Token Index: 208