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

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

Neuron 1388 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: 2.2761. Min Range: -2.2761

Max Act: 2.2761. Min Act: -0.0000

Data Index: 31620 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 2.2761. Min Range: -2.2761

Max Act: 2.0521. Min Act: -0.0000

Data Index: 547167 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 2.2761. Min Range: -2.2761

Max Act: 1.9863. Min Act: -0.0000

Data Index: 278759 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 2.2761. Min Range: -2.2761

Max Act: 1.8500. Min Act: -0.0000

Data Index: 485829 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 2.2761. Min Range: -2.2761

Max Act: 2.0016. Min Act: -0.0000

Data Index: 777508 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 2.2761. Min Range: -2.2761

Max Act: 1.8746. Min Act: -0.0000

Data Index: 484405 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 2.2761. Min Range: -2.2761

Max Act: 1.9051. Min Act: -0.0000

Data Index: 1273832 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 2.2761. Min Range: -2.2761

Max Act: 1.8951. Min Act: -0.0000

Data Index: 1164106 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 2.2761. Min Range: -2.2761

Max Act: 1.7695. Min Act: -0.0000

Data Index: 63392 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 2.2761. Min Range: -2.2761

Max Act: 1.8455. Min Act: -0.0000

Data Index: 880560 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 2.2761. Min Range: -2.2761

Max Act: 1.8521. Min Act: -0.0000

Data Index: 1290885 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 2.2761. Min Range: -2.2761

Max Act: 1.8488. Min Act: -0.0000

Data Index: 654394 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 2.2761. Min Range: -2.2761

Max Act: 1.9490. Min Act: -0.0000

Data Index: 1270449 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 2.2761. Min Range: -2.2761

Max Act: 1.8078. Min Act: -0.0000

Data Index: 545396 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 2.2761. Min Range: -2.2761

Max Act: 1.7814. Min Act: -0.0000

Data Index: 1330640 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 2.2761. Min Range: -2.2761

Max Act: 1.7931. Min Act: -0.0000

Data Index: 264635 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 2.2761. Min Range: -2.2761

Max Act: 1.7456. Min Act: -0.0000

Data Index: 870909 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 2.2761. Min Range: -2.2761

Max Act: 1.6646. Min Act: -0.0000

Data Index: 457557 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 2.2761. Min Range: -2.2761

Max Act: 1.6479. Min Act: -0.0000

Data Index: 306263 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 2.2761. Min Range: -2.2761

Max Act: 1.6232. Min Act: -0.0000

Data Index: 717593 (C4 (Web Text))

Max Activating Token Index: 974