Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3417 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.1721. Min Act: -0.0000

Data Index: 682723 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.1222. Min Act: -0.0000

Data Index: 1475493 (Python Code)

Max Activating Token Index: 71

Text #2

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.0461. Min Act: -0.0000

Data Index: 1520797 (Python Code)

Max Activating Token Index: 139

Text #3

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.1119. Min Act: -0.0000

Data Index: 402541 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.0355. Min Act: -0.0000

Data Index: 581624 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.0659. Min Act: -0.0000

Data Index: 945 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.0712. Min Act: -0.0000

Data Index: 1469262 (Python Code)

Max Activating Token Index: 252

Text #7

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.0632. Min Act: -0.0000

Data Index: 902526 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.1254. Min Act: -0.0000

Data Index: 1505998 (Python Code)

Max Activating Token Index: 672

Text #9

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.0478. Min Act: -0.0000

Data Index: 897208 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.0300. Min Act: -0.0000

Data Index: 1521363 (Python Code)

Max Activating Token Index: 845

Text #11

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.9891. Min Act: -0.0000

Data Index: 121117 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1336024 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.9887. Min Act: -0.0000

Data Index: 1327992 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.9890. Min Act: -0.0000

Data Index: 1555750 (Python Code)

Max Activating Token Index: 973

Text #15

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.9524. Min Act: -0.0000

Data Index: 89748 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.9949. Min Act: -0.0000

Data Index: 1459725 (Python Code)

Max Activating Token Index: 25

Text #17

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.0032. Min Act: -0.0000

Data Index: 298975 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.9941. Min Act: -0.0000

Data Index: 944174 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.9300. Min Act: -0.0000

Data Index: 925039 (C4 (Web Text))

Max Activating Token Index: 113