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

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

Neuron 302 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0868. Min Range: -1.0868

Max Act: 1.0408. Min Act: -0.0001

Data Index: 957693 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 1.0868. Min Range: -1.0868

Max Act: 1.0868. Min Act: -0.0001

Data Index: 1184477 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.9147. Min Act: -0.0001

Data Index: 1040052 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8354. Min Act: -0.0001

Data Index: 1554100 (Python Code)

Max Activating Token Index: 95

Text #4

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.7530. Min Act: -0.0001

Data Index: 221826 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.9017. Min Act: -0.0001

Data Index: 985198 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8499. Min Act: -0.0001

Data Index: 670754 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8425. Min Act: -0.0001

Data Index: 389269 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8739. Min Act: -0.0001

Data Index: 300134 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8621. Min Act: -0.0001

Data Index: 523265 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8944. Min Act: -0.0001

Data Index: 1993 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8212. Min Act: -0.0001

Data Index: 1315794 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8425. Min Act: -0.0001

Data Index: 341572 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8350. Min Act: -0.0001

Data Index: 979870 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.7757. Min Act: -0.0001

Data Index: 557225 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8277. Min Act: -0.0001

Data Index: 893918 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8706. Min Act: -0.0001

Data Index: 980627 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.7581. Min Act: -0.0001

Data Index: 412819 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.7682. Min Act: -0.0001

Data Index: 94086 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.7916. Min Act: -0.0001

Data Index: 289329 (C4 (Web Text))

Max Activating Token Index: 379