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

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

Neuron 687 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.3034. Min Act: -0.0001

Data Index: 937314 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2964. Min Act: -0.0001

Data Index: 716613 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2843. Min Act: -0.0001

Data Index: 287650 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2986. Min Act: -0.0001

Data Index: 13035 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2655. Min Act: -0.0001

Data Index: 1075966 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2731. Min Act: -0.0001

Data Index: 824831 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2786. Min Act: -0.0001

Data Index: 973258 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2582. Min Act: -0.0001

Data Index: 798270 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2472. Min Act: -0.0001

Data Index: 628877 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2132. Min Act: -0.0001

Data Index: 1171931 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2381. Min Act: -0.0001

Data Index: 364325 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2411. Min Act: -0.0001

Data Index: 349918 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2566. Min Act: -0.0001

Data Index: 1166934 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2742. Min Act: -0.0001

Data Index: 887029 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2471. Min Act: -0.0001

Data Index: 490078 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2552. Min Act: -0.0001

Data Index: 1175825 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2162. Min Act: -0.0001

Data Index: 25114 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2536. Min Act: -0.0001

Data Index: 541435 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2342. Min Act: -0.0001

Data Index: 72728 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2497. Min Act: -0.0001

Data Index: 108848 (C4 (Web Text))

Max Activating Token Index: 969