Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3884 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.8682. Min Range: -5.8682

Max Act: 5.8682. Min Act: -0.0000

Data Index: 438426 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 5.8682. Min Range: -5.8682

Max Act: 4.7818. Min Act: -0.0000

Data Index: 1347632 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 5.8682. Min Range: -5.8682

Max Act: 4.6191. Min Act: -0.0000

Data Index: 277743 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 5.8682. Min Range: -5.8682

Max Act: 4.5533. Min Act: -0.0000

Data Index: 989195 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 5.8682. Min Range: -5.8682

Max Act: 4.3464. Min Act: 0.0000

Data Index: 578016 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 5.8682. Min Range: -5.8682

Max Act: 4.5105. Min Act: -0.0000

Data Index: 848515 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 5.8682. Min Range: -5.8682

Max Act: 4.4718. Min Act: -0.0000

Data Index: 374426 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 5.8682. Min Range: -5.8682

Max Act: 4.1770. Min Act: -0.0000

Data Index: 1270680 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 5.8682. Min Range: -5.8682

Max Act: 3.7223. Min Act: -0.0000

Data Index: 1049337 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 5.8682. Min Range: -5.8682

Max Act: 3.7036. Min Act: -0.0000

Data Index: 1094146 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 5.8682. Min Range: -5.8682

Max Act: 3.8613. Min Act: -0.0000

Data Index: 1318931 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 5.8682. Min Range: -5.8682

Max Act: 3.8486. Min Act: -0.0000

Data Index: 329758 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 5.8682. Min Range: -5.8682

Max Act: 3.9825. Min Act: -0.0000

Data Index: 165204 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 5.8682. Min Range: -5.8682

Max Act: 3.7751. Min Act: -0.0000

Data Index: 1074138 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 5.8682. Min Range: -5.8682

Max Act: 3.5809. Min Act: -0.0000

Data Index: 6987 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 5.8682. Min Range: -5.8682

Max Act: 3.6223. Min Act: -0.0000

Data Index: 791059 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 5.8682. Min Range: -5.8682

Max Act: 3.6070. Min Act: -0.0000

Data Index: 978803 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 5.8682. Min Range: -5.8682

Max Act: 3.4409. Min Act: -0.0000

Data Index: 588999 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 5.8682. Min Range: -5.8682

Max Act: 3.6127. Min Act: -0.0000

Data Index: 387106 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 5.8682. Min Range: -5.8682

Max Act: 3.3592. Min Act: -0.0000

Data Index: 938524 (C4 (Web Text))

Max Activating Token Index: 571