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

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

Neuron 911 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3188. Min Range: -5.3188

Max Act: 5.3188. Min Act: -0.0000

Data Index: 745093 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 5.3188. Min Range: -5.3188

Max Act: 4.4401. Min Act: -0.0000

Data Index: 800742 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 5.3188. Min Range: -5.3188

Max Act: 3.9923. Min Act: -0.0001

Data Index: 1073557 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 5.3188. Min Range: -5.3188

Max Act: 3.9084. Min Act: -0.0001

Data Index: 348880 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 5.3188. Min Range: -5.3188

Max Act: 3.9968. Min Act: -0.0000

Data Index: 71190 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 5.3188. Min Range: -5.3188

Max Act: 4.1474. Min Act: -0.0000

Data Index: 360367 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 5.3188. Min Range: -5.3188

Max Act: 3.6521. Min Act: -0.0000

Data Index: 187280 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 5.3188. Min Range: -5.3188

Max Act: 3.4362. Min Act: -0.0001

Data Index: 494910 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 5.3188. Min Range: -5.3188

Max Act: 3.8756. Min Act: -0.0000

Data Index: 860519 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 5.3188. Min Range: -5.3188

Max Act: 3.3356. Min Act: -0.0000

Data Index: 552993 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 5.3188. Min Range: -5.3188

Max Act: 3.4507. Min Act: -0.0000

Data Index: 365055 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 5.3188. Min Range: -5.3188

Max Act: 3.2830. Min Act: -0.0000

Data Index: 969226 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 5.3188. Min Range: -5.3188

Max Act: 3.4219. Min Act: -0.0000

Data Index: 13558 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 5.3188. Min Range: -5.3188

Max Act: 3.3660. Min Act: -0.0000

Data Index: 486418 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 5.3188. Min Range: -5.3188

Max Act: 3.0642. Min Act: -0.0000

Data Index: 1135 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 5.3188. Min Range: -5.3188

Max Act: 3.2032. Min Act: -0.0000

Data Index: 48961 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 5.3188. Min Range: -5.3188

Max Act: 3.2877. Min Act: -0.0000

Data Index: 136770 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 5.3188. Min Range: -5.3188

Max Act: 3.2975. Min Act: -0.0000

Data Index: 450179 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 5.3188. Min Range: -5.3188

Max Act: 3.1042. Min Act: -0.0000

Data Index: 22270 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 5.3188. Min Range: -5.3188

Max Act: 2.9632. Min Act: -0.0000

Data Index: 153230 (C4 (Web Text))

Max Activating Token Index: 905