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

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

Neuron 875 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1145. Min Act: -0.0000

Data Index: 678931 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1073. Min Act: -0.0000

Data Index: 79007 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1085. Min Act: -0.0000

Data Index: 130494 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1009. Min Act: -0.0000

Data Index: 424119 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0995. Min Act: -0.0000

Data Index: 1321745 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0916. Min Act: -0.0000

Data Index: 749368 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1185272 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0906. Min Act: -0.0000

Data Index: 194059 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0895. Min Act: -0.0000

Data Index: 1288546 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0898. Min Act: -0.0000

Data Index: 301136 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0854. Min Act: -0.0000

Data Index: 1013692 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1070835 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0811. Min Act: -0.0000

Data Index: 394873 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0874. Min Act: -0.0000

Data Index: 836397 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0836. Min Act: -0.0000

Data Index: 319218 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0865. Min Act: -0.0000

Data Index: 130511 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1169039 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0841. Min Act: -0.0000

Data Index: 959862 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0818. Min Act: -0.0000

Data Index: 406017 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1351400 (C4 (Web Text))

Max Activating Token Index: 386