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

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

Neuron 641 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.4570. Min Act: -0.0000

Data Index: 1353899 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 3.4570. Min Range: -3.4570

Max Act: 2.9838. Min Act: -0.0000

Data Index: 1156739 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.0699. Min Act: -0.0000

Data Index: 554921 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 3.4570. Min Range: -3.4570

Max Act: 2.8089. Min Act: -0.0000

Data Index: 992448 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 3.4570. Min Range: -3.4570

Max Act: 2.6216. Min Act: -0.0000

Data Index: 1271215 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 3.4570. Min Range: -3.4570

Max Act: 2.7129. Min Act: -0.0000

Data Index: 908547 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 3.4570. Min Range: -3.4570

Max Act: 2.7362. Min Act: -0.0000

Data Index: 111445 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 3.4570. Min Range: -3.4570

Max Act: 2.3401. Min Act: -0.0000

Data Index: 1335966 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 3.4570. Min Range: -3.4570

Max Act: 2.1888. Min Act: -0.0000

Data Index: 1314012 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 3.4570. Min Range: -3.4570

Max Act: 2.1474. Min Act: -0.0000

Data Index: 26938 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 3.4570. Min Range: -3.4570

Max Act: 2.2136. Min Act: -0.0000

Data Index: 25027 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 3.4570. Min Range: -3.4570

Max Act: 2.2051. Min Act: -0.0000

Data Index: 392821 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 3.4570. Min Range: -3.4570

Max Act: 1.9669. Min Act: -0.0000

Data Index: 604062 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 3.4570. Min Range: -3.4570

Max Act: 2.2531. Min Act: -0.0000

Data Index: 779422 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 3.4570. Min Range: -3.4570

Max Act: 2.2437. Min Act: -0.0001

Data Index: 95961 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 3.4570. Min Range: -3.4570

Max Act: 2.2484. Min Act: -0.0000

Data Index: 212967 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 3.4570. Min Range: -3.4570

Max Act: 2.0155. Min Act: -0.0000

Data Index: 1033723 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 3.4570. Min Range: -3.4570

Max Act: 2.0097. Min Act: -0.0000

Data Index: 1053433 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 3.4570. Min Range: -3.4570

Max Act: 2.2120. Min Act: -0.0000

Data Index: 23234 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 3.4570. Min Range: -3.4570

Max Act: 1.8584. Min Act: -0.0000

Data Index: 1288170 (C4 (Web Text))

Max Activating Token Index: 302