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

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

Neuron 3007 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.9753. Min Act: -0.0000

Data Index: 905923 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.6639. Min Act: -0.0000

Data Index: 1229879 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.6321. Min Act: -0.0000

Data Index: 1234956 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.5493. Min Act: -0.0000

Data Index: 383046 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.5374. Min Act: -0.0000

Data Index: 166482 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.4171. Min Act: -0.0000

Data Index: 390375 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.4333. Min Act: -0.0000

Data Index: 475351 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.4046. Min Act: -0.0000

Data Index: 145701 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.3608. Min Act: -0.0000

Data Index: 485509 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.4374. Min Act: -0.0000

Data Index: 499383 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.3490. Min Act: -0.0000

Data Index: 1611531 (Python Code)

Max Activating Token Index: 357

Text #11

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.3948. Min Act: -0.0000

Data Index: 1649370 (Python Code)

Max Activating Token Index: 303

Text #12

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.3144. Min Act: -0.0000

Data Index: 1515837 (Python Code)

Max Activating Token Index: 850

Text #13

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.3866. Min Act: -0.0000

Data Index: 1305993 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.3689. Min Act: -0.0000

Data Index: 965027 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.3484. Min Act: -0.0000

Data Index: 893095 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.3506. Min Act: -0.0000

Data Index: 829170 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.3223. Min Act: -0.0000

Data Index: 72939 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.2528. Min Act: -0.0000

Data Index: 86902 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.3225. Min Act: -0.0000

Data Index: 689920 (C4 (Web Text))

Max Activating Token Index: 112