Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 29 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5679. Min Act: -0.0001

Data Index: 186949 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5294. Min Act: -0.0001

Data Index: 626017 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4555. Min Act: -0.0001

Data Index: 872517 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4466. Min Act: -0.0001

Data Index: 1311610 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4118. Min Act: -0.0001

Data Index: 266860 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4231. Min Act: -0.0001

Data Index: 1082435 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3818. Min Act: -0.0001

Data Index: 626105 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4218. Min Act: -0.0001

Data Index: 1281486 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3943. Min Act: -0.0001

Data Index: 647548 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4290. Min Act: -0.0001

Data Index: 1062265 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4082. Min Act: -0.0001

Data Index: 73093 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3669. Min Act: -0.0001

Data Index: 1038994 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3812. Min Act: -0.0001

Data Index: 4604 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3936. Min Act: -0.0001

Data Index: 1208476 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3764. Min Act: -0.0001

Data Index: 1176873 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3486. Min Act: -0.0001

Data Index: 741812 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3351. Min Act: -0.0001

Data Index: 492214 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3566. Min Act: -0.0001

Data Index: 976855 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3662. Min Act: -0.0001

Data Index: 1277564 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3639. Min Act: -0.0001

Data Index: 483722 (C4 (Web Text))

Max Activating Token Index: 699