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

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

Neuron 3092 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2617. Min Act: -0.0001

Data Index: 680461 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2725. Min Act: -0.0000

Data Index: 665078 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1180551 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1053841 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2032. Min Act: -0.0000

Data Index: 800211 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2162. Min Act: -0.0000

Data Index: 1094073 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2051. Min Act: -0.0000

Data Index: 458419 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1970. Min Act: -0.0000

Data Index: 670658 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1254012 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1340812 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2161. Min Act: -0.0001

Data Index: 176195 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1076870 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1883. Min Act: -0.0000

Data Index: 918436 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1861. Min Act: -0.0000

Data Index: 770109 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1915. Min Act: -0.0000

Data Index: 213831 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1836. Min Act: -0.0000

Data Index: 981111 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1951. Min Act: -0.0000

Data Index: 636031 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1901. Min Act: -0.0001

Data Index: 193146 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1954. Min Act: -0.0000

Data Index: 450193 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1861. Min Act: -0.0000

Data Index: 160447 (C4 (Web Text))

Max Activating Token Index: 710