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

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

Neuron 1441 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.3838. Min Act: -0.0000

Data Index: 348844 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.3082. Min Act: -0.0000

Data Index: 1139973 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.1752. Min Act: -0.0000

Data Index: 628558 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.0500. Min Act: -0.0000

Data Index: 929809 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.1346. Min Act: -0.0000

Data Index: 1309133 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.0074. Min Act: -0.0000

Data Index: 835756 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 1.3838. Min Range: -1.3838

Max Act: 0.9969. Min Act: -0.0000

Data Index: 1336013 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.0462. Min Act: -0.0000

Data Index: 183808 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 1.3838. Min Range: -1.3838

Max Act: 1.0100. Min Act: -0.0000

Data Index: 440808 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 1.3838. Min Range: -1.3838

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1340300 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 1.3838. Min Range: -1.3838

Max Act: 0.9972. Min Act: -0.0000

Data Index: 377985 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 1.3838. Min Range: -1.3838

Max Act: 0.8934. Min Act: -0.0000

Data Index: 195678 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 1.3838. Min Range: -1.3838

Max Act: 0.9680. Min Act: -0.0000

Data Index: 1340556 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 1.3838. Min Range: -1.3838

Max Act: 0.9681. Min Act: -0.0000

Data Index: 1235483 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 1.3838. Min Range: -1.3838

Max Act: 0.8698. Min Act: -0.0000

Data Index: 178495 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 1.3838. Min Range: -1.3838

Max Act: 0.9133. Min Act: -0.0000

Data Index: 1270571 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 1.3838. Min Range: -1.3838

Max Act: 0.8793. Min Act: -0.0000

Data Index: 666925 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 1.3838. Min Range: -1.3838

Max Act: 0.8565. Min Act: -0.0000

Data Index: 1102918 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 1.3838. Min Range: -1.3838

Max Act: 0.8933. Min Act: -0.0000

Data Index: 73343 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 1.3838. Min Range: -1.3838

Max Act: 0.9393. Min Act: -0.0000

Data Index: 952697 (C4 (Web Text))

Max Activating Token Index: 435