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

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

Neuron 1972 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: 1.2296. Min Range: -1.2296

Max Act: 1.2296. Min Act: -0.0000

Data Index: 156606 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 1.2296. Min Range: -1.2296

Max Act: 1.0128. Min Act: -0.0000

Data Index: 209457 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9965. Min Act: -0.0000

Data Index: 421799 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9172. Min Act: -0.0000

Data Index: 36279 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1144412 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9063. Min Act: -0.0000

Data Index: 656909 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9151. Min Act: -0.0000

Data Index: 270151 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9082. Min Act: -0.0000

Data Index: 491990 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8832. Min Act: -0.0000

Data Index: 52452 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8794. Min Act: -0.0000

Data Index: 434602 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8723. Min Act: -0.0000

Data Index: 846148 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9331. Min Act: -0.0000

Data Index: 9336 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1057590 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9519. Min Act: -0.0000

Data Index: 1315579 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9211. Min Act: -0.0000

Data Index: 1193206 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8314. Min Act: -0.0000

Data Index: 758905 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8865. Min Act: -0.0000

Data Index: 1115931 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8573. Min Act: -0.0000

Data Index: 1058586 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9065. Min Act: -0.0000

Data Index: 964278 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8304. Min Act: -0.0000

Data Index: 494279 (C4 (Web Text))

Max Activating Token Index: 556