Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2650 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1107. Min Act: -0.0003

Data Index: 431707 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1142. Min Act: -0.0003

Data Index: 691092 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1030. Min Act: -0.0003

Data Index: 392231 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1036. Min Act: -0.0003

Data Index: 526949 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0885. Min Act: -0.0003

Data Index: 970852 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0884. Min Act: -0.0003

Data Index: 643989 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0967. Min Act: -0.0003

Data Index: 806518 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0886. Min Act: -0.0003

Data Index: 1291278 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0873. Min Act: -0.0003

Data Index: 870187 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0834. Min Act: -0.0003

Data Index: 1335773 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0916. Min Act: -0.0003

Data Index: 273183 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0796. Min Act: -0.0003

Data Index: 1302014 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0788. Min Act: -0.0004

Data Index: 664722 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0853. Min Act: -0.0003

Data Index: 532699 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0843. Min Act: -0.0003

Data Index: 442273 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0844. Min Act: -0.0003

Data Index: 516775 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0868. Min Act: -0.0003

Data Index: 1175722 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0803. Min Act: -0.0003

Data Index: 994961 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0834. Min Act: -0.0003

Data Index: 1259677 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0846. Min Act: -0.0003

Data Index: 1178831 (C4 (Web Text))

Max Activating Token Index: 273