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

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

Neuron 436 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8166. Min Range: -2.8166

Max Act: 2.7125. Min Act: -0.0000

Data Index: 311479 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 2.8166. Min Range: -2.8166

Max Act: 2.8166. Min Act: -0.0000

Data Index: 345962 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 2.8166. Min Range: -2.8166

Max Act: 2.7059. Min Act: -0.0000

Data Index: 919357 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 2.8166. Min Range: -2.8166

Max Act: 2.5505. Min Act: -0.0000

Data Index: 1207857 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 2.8166. Min Range: -2.8166

Max Act: 2.6312. Min Act: -0.0000

Data Index: 1177715 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 2.8166. Min Range: -2.8166

Max Act: 2.7627. Min Act: -0.0000

Data Index: 13885 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 2.8166. Min Range: -2.8166

Max Act: 2.5037. Min Act: -0.0000

Data Index: 513624 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 2.8166. Min Range: -2.8166

Max Act: 2.7044. Min Act: -0.0000

Data Index: 216477 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 2.8166. Min Range: -2.8166

Max Act: 2.4412. Min Act: -0.0000

Data Index: 68184 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 2.8166. Min Range: -2.8166

Max Act: 2.1996. Min Act: -0.0000

Data Index: 831493 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 2.8166. Min Range: -2.8166

Max Act: 2.1190. Min Act: -0.0000

Data Index: 1100858 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 2.8166. Min Range: -2.8166

Max Act: 2.0661. Min Act: -0.0000

Data Index: 1230363 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 2.8166. Min Range: -2.8166

Max Act: 2.1779. Min Act: -0.0000

Data Index: 173453 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 2.8166. Min Range: -2.8166

Max Act: 2.1125. Min Act: -0.0000

Data Index: 633571 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.9594. Min Act: -0.0000

Data Index: 414473 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 2.8166. Min Range: -2.8166

Max Act: 2.0773. Min Act: -0.0000

Data Index: 9711 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.8218. Min Act: -0.0000

Data Index: 749538 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.8910. Min Act: -0.0000

Data Index: 760189 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.8879. Min Act: -0.0000

Data Index: 445657 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.9535. Min Act: -0.0000

Data Index: 716938 (C4 (Web Text))

Max Activating Token Index: 180