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

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

Neuron 5198 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: 2.2080. Min Range: -2.2080

Max Act: 2.2080. Min Act: 0.0000

Data Index: 1372465 (Python Code)

Max Activating Token Index: 40

Text #1

Max Range: 2.2080. Min Range: -2.2080

Max Act: 2.1782. Min Act: -0.0000

Data Index: 1362211 (Python Code)

Max Activating Token Index: 735

Text #2

Max Range: 2.2080. Min Range: -2.2080

Max Act: 1.8994. Min Act: -0.0000

Data Index: 238338 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 2.2080. Min Range: -2.2080

Max Act: 1.8677. Min Act: -0.0000

Data Index: 717914 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 2.2080. Min Range: -2.2080

Max Act: 1.8519. Min Act: -0.0000

Data Index: 1441637 (Python Code)

Max Activating Token Index: 524

Text #5

Max Range: 2.2080. Min Range: -2.2080

Max Act: 1.8301. Min Act: -0.0000

Data Index: 1614993 (Python Code)

Max Activating Token Index: 76

Text #6

Max Range: 2.2080. Min Range: -2.2080

Max Act: 1.7797. Min Act: -0.0000

Data Index: 199213 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 2.2080. Min Range: -2.2080

Max Act: 1.7962. Min Act: -0.0000

Data Index: 447682 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 2.2080. Min Range: -2.2080

Max Act: 1.7118. Min Act: -0.0000

Data Index: 1376080 (Python Code)

Max Activating Token Index: 230

Text #9

Max Range: 2.2080. Min Range: -2.2080

Max Act: 1.7119. Min Act: -0.0000

Data Index: 1496725 (Python Code)

Max Activating Token Index: 692

Text #10

Max Range: 2.2080. Min Range: -2.2080

Max Act: 1.7032. Min Act: -0.0000

Data Index: 1408645 (Python Code)

Max Activating Token Index: 387

Text #11

Max Range: 2.2080. Min Range: -2.2080

Max Act: 1.7383. Min Act: -0.0000

Data Index: 1049402 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 2.2080. Min Range: -2.2080

Max Act: 1.7020. Min Act: -0.0000

Data Index: 162158 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 2.2080. Min Range: -2.2080

Max Act: 1.6859. Min Act: -0.0000

Data Index: 1639032 (Python Code)

Max Activating Token Index: 958

Text #14

Max Range: 2.2080. Min Range: -2.2080

Max Act: 1.5585. Min Act: -0.0000

Data Index: 1376341 (Python Code)

Max Activating Token Index: 423

Text #15

Max Range: 2.2080. Min Range: -2.2080

Max Act: 1.5684. Min Act: -0.0000

Data Index: 1154505 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 2.2080. Min Range: -2.2080

Max Act: 1.6459. Min Act: -0.0000

Data Index: 394935 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 2.2080. Min Range: -2.2080

Max Act: 1.6153. Min Act: -0.0000

Data Index: 1508520 (Python Code)

Max Activating Token Index: 662

Text #18

Max Range: 2.2080. Min Range: -2.2080

Max Act: 1.5985. Min Act: -0.0000

Data Index: 769897 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 2.2080. Min Range: -2.2080

Max Act: 1.5623. Min Act: -0.0000

Data Index: 1329046 (C4 (Web Text))

Max Activating Token Index: 344