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

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

Neuron 5105 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.3113. Min Act: -0.0000

Data Index: 911009 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.2589. Min Act: -0.0000

Data Index: 330016 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.2364. Min Act: -0.0000

Data Index: 1281423 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.1228. Min Act: -0.0000

Data Index: 1067273 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.3475. Min Act: -0.0000

Data Index: 763010 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.2805. Min Act: -0.0000

Data Index: 21859 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.2873. Min Act: -0.0000

Data Index: 1094801 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.2401. Min Act: -0.0000

Data Index: 552869 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.1233. Min Act: -0.0000

Data Index: 572779 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.1172. Min Act: -0.0000

Data Index: 446355 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.1117. Min Act: -0.0000

Data Index: 1321585 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.1512. Min Act: -0.0000

Data Index: 778172 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.1587. Min Act: -0.0000

Data Index: 889597 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.0912. Min Act: -0.0000

Data Index: 632232 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.0952. Min Act: -0.0000

Data Index: 352807 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.1025. Min Act: -0.0000

Data Index: 1197597 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.1326. Min Act: -0.0000

Data Index: 1077449 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.0950. Min Act: -0.0000

Data Index: 370963 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.0605. Min Act: -0.0000

Data Index: 336590 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.0150. Min Act: -0.0000

Data Index: 679050 (C4 (Web Text))

Max Activating Token Index: 300