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

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

Neuron 237 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: 2.3877. Min Range: -2.3877

Max Act: 2.3877. Min Act: -0.0000

Data Index: 1562992 (Python Code)

Max Activating Token Index: 599

Text #1

Max Range: 2.3877. Min Range: -2.3877

Max Act: 2.0754. Min Act: -0.0000

Data Index: 1504695 (Python Code)

Max Activating Token Index: 607

Text #2

Max Range: 2.3877. Min Range: -2.3877

Max Act: 1.6967. Min Act: -0.0000

Data Index: 824844 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 2.3877. Min Range: -2.3877

Max Act: 1.8200. Min Act: -0.0000

Data Index: 65178 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 2.3877. Min Range: -2.3877

Max Act: 1.7125. Min Act: -0.0000

Data Index: 134142 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 2.3877. Min Range: -2.3877

Max Act: 1.5455. Min Act: -0.0000

Data Index: 1125081 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 2.3877. Min Range: -2.3877

Max Act: 1.4623. Min Act: -0.0000

Data Index: 1298779 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 2.3877. Min Range: -2.3877

Max Act: 1.4054. Min Act: -0.0000

Data Index: 49171 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 2.3877. Min Range: -2.3877

Max Act: 1.3923. Min Act: -0.0000

Data Index: 54298 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 2.3877. Min Range: -2.3877

Max Act: 1.3828. Min Act: -0.0000

Data Index: 658448 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 2.3877. Min Range: -2.3877

Max Act: 1.2472. Min Act: -0.0000

Data Index: 390334 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 2.3877. Min Range: -2.3877

Max Act: 1.2534. Min Act: -0.0000

Data Index: 1262655 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 2.3877. Min Range: -2.3877

Max Act: 1.1395. Min Act: -0.0000

Data Index: 135080 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 2.3877. Min Range: -2.3877

Max Act: 1.3561. Min Act: -0.0000

Data Index: 402048 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 2.3877. Min Range: -2.3877

Max Act: 1.2813. Min Act: -0.0000

Data Index: 29777 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 2.3877. Min Range: -2.3877

Max Act: 1.1565. Min Act: -0.0000

Data Index: 183633 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 2.3877. Min Range: -2.3877

Max Act: 1.2132. Min Act: -0.0000

Data Index: 40029 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 2.3877. Min Range: -2.3877

Max Act: 1.2241. Min Act: -0.0000

Data Index: 520926 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 2.3877. Min Range: -2.3877

Max Act: 1.3143. Min Act: -0.0000

Data Index: 1490351 (Python Code)

Max Activating Token Index: 72

Text #19

Max Range: 2.3877. Min Range: -2.3877

Max Act: 1.2979. Min Act: -0.0000

Data Index: 194493 (C4 (Web Text))

Max Activating Token Index: 316