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

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

Neuron 3942 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1050431 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6970. Min Act: -0.0000

Data Index: 978305 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6035. Min Act: -0.0000

Data Index: 315895 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1270705 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1297988 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5180. Min Act: -0.0000

Data Index: 1094482 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5123. Min Act: -0.0000

Data Index: 28762 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5072. Min Act: -0.0000

Data Index: 1195991 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4571. Min Act: -0.0000

Data Index: 144058 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4923. Min Act: -0.0000

Data Index: 914974 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4441. Min Act: -0.0000

Data Index: 1330702 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1111142 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4685. Min Act: -0.0000

Data Index: 168126 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4676. Min Act: -0.0000

Data Index: 596690 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4537. Min Act: -0.0000

Data Index: 469908 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4557. Min Act: -0.0000

Data Index: 294546 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4042. Min Act: -0.0000

Data Index: 866524 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1043876 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1354800 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.4178. Min Act: -0.0000

Data Index: 490153 (C4 (Web Text))

Max Activating Token Index: 45