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

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

Neuron 3199 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5914. Min Act: -0.0001

Data Index: 582363 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.6048. Min Act: -0.0001

Data Index: 1111789 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5994. Min Act: -0.0001

Data Index: 1222787 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5771. Min Act: -0.0001

Data Index: 814210 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5521. Min Act: -0.0001

Data Index: 1036888 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5086. Min Act: -0.0001

Data Index: 153078 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5113. Min Act: -0.0001

Data Index: 967576 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5156. Min Act: -0.0001

Data Index: 830454 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5076. Min Act: -0.0001

Data Index: 168734 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5081. Min Act: -0.0001

Data Index: 637065 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5049. Min Act: -0.0001

Data Index: 1173076 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4987. Min Act: -0.0001

Data Index: 1101842 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4964. Min Act: -0.0001

Data Index: 348491 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4715. Min Act: -0.0001

Data Index: 654519 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4726. Min Act: -0.0001

Data Index: 806984 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4696. Min Act: -0.0001

Data Index: 1073603 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4983. Min Act: -0.0001

Data Index: 829109 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4972. Min Act: -0.0001

Data Index: 479661 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4720. Min Act: -0.0001

Data Index: 821790 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4730. Min Act: -0.0001

Data Index: 380881 (C4 (Web Text))

Max Activating Token Index: 101