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

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

Neuron 5528 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3048. Min Range: -5.3048

Max Act: 5.3048. Min Act: -0.0000

Data Index: 345711 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 5.3048. Min Range: -5.3048

Max Act: 4.7726. Min Act: -0.0000

Data Index: 791100 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 5.3048. Min Range: -5.3048

Max Act: 4.6350. Min Act: -0.0000

Data Index: 519494 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 5.3048. Min Range: -5.3048

Max Act: 4.4061. Min Act: -0.0000

Data Index: 590693 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 5.3048. Min Range: -5.3048

Max Act: 4.3386. Min Act: -0.0000

Data Index: 1251869 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 5.3048. Min Range: -5.3048

Max Act: 4.2245. Min Act: -0.0000

Data Index: 588212 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 5.3048. Min Range: -5.3048

Max Act: 4.0318. Min Act: -0.0000

Data Index: 183015 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 5.3048. Min Range: -5.3048

Max Act: 3.8741. Min Act: -0.0000

Data Index: 1332485 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 5.3048. Min Range: -5.3048

Max Act: 3.7736. Min Act: -0.0000

Data Index: 409993 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 5.3048. Min Range: -5.3048

Max Act: 3.7132. Min Act: -0.0000

Data Index: 23194 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 5.3048. Min Range: -5.3048

Max Act: 3.6655. Min Act: -0.0000

Data Index: 1319320 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 5.3048. Min Range: -5.3048

Max Act: 3.6451. Min Act: -0.0000

Data Index: 1052923 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 5.3048. Min Range: -5.3048

Max Act: 3.6082. Min Act: -0.0000

Data Index: 202286 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 5.3048. Min Range: -5.3048

Max Act: 3.5679. Min Act: -0.0000

Data Index: 1088919 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 5.3048. Min Range: -5.3048

Max Act: 3.5179. Min Act: -0.0000

Data Index: 1315617 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 5.3048. Min Range: -5.3048

Max Act: 3.6072. Min Act: -0.0000

Data Index: 468062 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 5.3048. Min Range: -5.3048

Max Act: 3.1656. Min Act: -0.0000

Data Index: 773423 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 5.3048. Min Range: -5.3048

Max Act: 3.0936. Min Act: -0.0000

Data Index: 15949 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 5.3048. Min Range: -5.3048

Max Act: 3.0779. Min Act: -0.0000

Data Index: 1305758 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 5.3048. Min Range: -5.3048

Max Act: 3.1914. Min Act: -0.0000

Data Index: 1078212 (C4 (Web Text))

Max Activating Token Index: 324