Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3033 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3813. Min Act: -0.0000

Data Index: 112490 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3885. Min Act: -0.0000

Data Index: 160991 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3589. Min Act: -0.0000

Data Index: 649891 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3474. Min Act: -0.0000

Data Index: 843342 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3391. Min Act: -0.0000

Data Index: 85207 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1297314 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3056. Min Act: -0.0000

Data Index: 534467 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2778. Min Act: -0.0000

Data Index: 74396 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2846. Min Act: -0.0000

Data Index: 1094684 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2740. Min Act: -0.0000

Data Index: 549977 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2639. Min Act: -0.0000

Data Index: 113732 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2788. Min Act: -0.0000

Data Index: 918043 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2791. Min Act: -0.0000

Data Index: 736343 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2840. Min Act: -0.0000

Data Index: 97906 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2731. Min Act: -0.0000

Data Index: 20213 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2541. Min Act: -0.0000

Data Index: 845006 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2659. Min Act: -0.0000

Data Index: 192594 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2712. Min Act: -0.0000

Data Index: 582306 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1264878 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2715. Min Act: -0.0000

Data Index: 1096070 (C4 (Web Text))

Max Activating Token Index: 423