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

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

Neuron 5838 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: 0.8072. Min Range: -0.8072

Max Act: 0.8072. Min Act: -0.0000

Data Index: 1324936 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.8036. Min Act: -0.0000

Data Index: 985591 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1434194 (Python Code)

Max Activating Token Index: 88

Text #3

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.7747. Min Act: -0.0000

Data Index: 528751 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.7592. Min Act: -0.0000

Data Index: 996558 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.7635. Min Act: -0.0000

Data Index: 1274598 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.7923. Min Act: -0.0000

Data Index: 150508 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.6870. Min Act: -0.0000

Data Index: 899166 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.7328. Min Act: -0.0000

Data Index: 118667 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.7284. Min Act: -0.0000

Data Index: 214833 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.7244. Min Act: 0.0000

Data Index: 1231278 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.7238. Min Act: -0.0000

Data Index: 1250042 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.7221. Min Act: -0.0000

Data Index: 335976 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.7179. Min Act: -0.0000

Data Index: 519496 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.6560. Min Act: -0.0000

Data Index: 1261127 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1169924 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.6953. Min Act: 0.0000

Data Index: 6092 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.6800. Min Act: 0.0000

Data Index: 392512 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.6847. Min Act: -0.0000

Data Index: 146405 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1192508 (C4 (Web Text))

Max Activating Token Index: 371