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

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

Neuron 2109 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: 0.1072. Min Range: -0.1072

Max Act: 0.1072. Min Act: -0.0003

Data Index: 975989 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0956. Min Act: -0.0003

Data Index: 1087933 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0971. Min Act: -0.0003

Data Index: 1305189 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0977. Min Act: -0.0003

Data Index: 131995 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.1000. Min Act: -0.0003

Data Index: 574048 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0951. Min Act: -0.0003

Data Index: 441867 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0927. Min Act: -0.0003

Data Index: 847543 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0858. Min Act: -0.0003

Data Index: 1350205 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0879. Min Act: -0.0003

Data Index: 429110 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0912. Min Act: -0.0003

Data Index: 993532 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0906. Min Act: -0.0003

Data Index: 318364 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0926. Min Act: -0.0003

Data Index: 644039 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0899. Min Act: -0.0003

Data Index: 980295 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0835. Min Act: -0.0003

Data Index: 72765 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0911. Min Act: -0.0003

Data Index: 740907 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0811. Min Act: -0.0003

Data Index: 786467 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0837. Min Act: -0.0003

Data Index: 163179 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0830. Min Act: -0.0003

Data Index: 570791 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0846. Min Act: -0.0003

Data Index: 254479 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0826. Min Act: -0.0003

Data Index: 736956 (C4 (Web Text))

Max Activating Token Index: 988