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

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

Neuron 1348 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.7600. Min Act: 0.0000

Data Index: 816349 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.6330. Min Act: 0.0000

Data Index: 487951 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.6162. Min Act: -0.0000

Data Index: 486422 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5887. Min Act: 0.0000

Data Index: 77578 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5694. Min Act: -0.0000

Data Index: 162496 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5713. Min Act: -0.0000

Data Index: 415045 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1123222 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5416. Min Act: -0.0000

Data Index: 246567 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.4843. Min Act: -0.0000

Data Index: 462430 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.4950. Min Act: -0.0000

Data Index: 29998 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.4575. Min Act: -0.0000

Data Index: 650346 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.4739. Min Act: 0.0000

Data Index: 1262030 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.4191. Min Act: -0.0000

Data Index: 311264 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.4559. Min Act: -0.0000

Data Index: 253797 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.3795. Min Act: -0.0000

Data Index: 818239 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.3253. Min Act: -0.0000

Data Index: 1132310 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.3574. Min Act: -0.0000

Data Index: 1283858 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.3298. Min Act: -0.0000

Data Index: 949168 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.3518. Min Act: -0.0000

Data Index: 510872 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.3533. Min Act: -0.0000

Data Index: 970129 (C4 (Web Text))

Max Activating Token Index: 296