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

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

Neuron 3980 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3858. Min Range: -2.3858

Max Act: 2.3858. Min Act: -0.0000

Data Index: 841752 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 2.3858. Min Range: -2.3858

Max Act: 2.1309. Min Act: -0.0000

Data Index: 246287 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 2.3858. Min Range: -2.3858

Max Act: 1.9568. Min Act: -0.0000

Data Index: 864183 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 2.3858. Min Range: -2.3858

Max Act: 1.8113. Min Act: -0.0000

Data Index: 180512 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 2.3858. Min Range: -2.3858

Max Act: 1.6470. Min Act: -0.0000

Data Index: 140045 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 2.3858. Min Range: -2.3858

Max Act: 1.5701. Min Act: -0.0000

Data Index: 657637 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 2.3858. Min Range: -2.3858

Max Act: 1.6019. Min Act: -0.0000

Data Index: 1625509 (Python Code)

Max Activating Token Index: 753

Text #7

Max Range: 2.3858. Min Range: -2.3858

Max Act: 1.6016. Min Act: -0.0000

Data Index: 378003 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 2.3858. Min Range: -2.3858

Max Act: 1.4782. Min Act: -0.0000

Data Index: 1266476 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 2.3858. Min Range: -2.3858

Max Act: 1.5190. Min Act: -0.0000

Data Index: 198359 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 2.3858. Min Range: -2.3858

Max Act: 1.3802. Min Act: -0.0000

Data Index: 555893 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 2.3858. Min Range: -2.3858

Max Act: 1.5005. Min Act: -0.0000

Data Index: 777519 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 2.3858. Min Range: -2.3858

Max Act: 1.4021. Min Act: -0.0000

Data Index: 935218 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 2.3858. Min Range: -2.3858

Max Act: 1.5708. Min Act: -0.0000

Data Index: 1160027 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 2.3858. Min Range: -2.3858

Max Act: 1.4887. Min Act: -0.0000

Data Index: 330674 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 2.3858. Min Range: -2.3858

Max Act: 1.4442. Min Act: -0.0000

Data Index: 715074 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 2.3858. Min Range: -2.3858

Max Act: 1.4581. Min Act: -0.0000

Data Index: 642651 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 2.3858. Min Range: -2.3858

Max Act: 1.5416. Min Act: -0.0000

Data Index: 681965 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 2.3858. Min Range: -2.3858

Max Act: 1.4643. Min Act: -0.0000

Data Index: 1282009 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 2.3858. Min Range: -2.3858

Max Act: 1.4306. Min Act: -0.0000

Data Index: 948649 (C4 (Web Text))

Max Activating Token Index: 320