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

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

Neuron 6104 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: 1.2823. Min Range: -1.2823

Max Act: 1.2823. Min Act: -0.0000

Data Index: 1320917 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 1.2823. Min Range: -1.2823

Max Act: 1.1456. Min Act: -0.0000

Data Index: 1095067 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 1.2823. Min Range: -1.2823

Max Act: 1.2124. Min Act: -0.0000

Data Index: 688648 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 1.2823. Min Range: -1.2823

Max Act: 1.0977. Min Act: -0.0000

Data Index: 758645 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 1.2823. Min Range: -1.2823

Max Act: 1.1334. Min Act: -0.0000

Data Index: 763020 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 1.2823. Min Range: -1.2823

Max Act: 1.1234. Min Act: -0.0000

Data Index: 699123 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 1.2823. Min Range: -1.2823

Max Act: 1.0511. Min Act: -0.0000

Data Index: 578335 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 1.2823. Min Range: -1.2823

Max Act: 1.0191. Min Act: -0.0000

Data Index: 611366 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 1.2823. Min Range: -1.2823

Max Act: 1.0097. Min Act: -0.0000

Data Index: 594409 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 1.2823. Min Range: -1.2823

Max Act: 1.0440. Min Act: -0.0000

Data Index: 900114 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 1.2823. Min Range: -1.2823

Max Act: 1.0149. Min Act: -0.0000

Data Index: 142231 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.9181. Min Act: -0.0000

Data Index: 1125594 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 1.2823. Min Range: -1.2823

Max Act: 1.0026. Min Act: -0.0000

Data Index: 1157104 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 1.2823. Min Range: -1.2823

Max Act: 1.0130. Min Act: -0.0000

Data Index: 115255 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.9507. Min Act: -0.0000

Data Index: 995428 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.9800. Min Act: -0.0000

Data Index: 1175550 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.9397. Min Act: -0.0000

Data Index: 508116 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.9307. Min Act: -0.0000

Data Index: 458593 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.9703. Min Act: -0.0000

Data Index: 1357157 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 1.2823. Min Range: -1.2823

Max Act: 1.0016. Min Act: -0.0000

Data Index: 778651 (C4 (Web Text))

Max Activating Token Index: 304