Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1138 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.3028. Min Act: -0.0001

Data Index: 1269394 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2401. Min Act: -0.0001

Data Index: 1237788 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2556. Min Act: -0.0001

Data Index: 83469 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2642. Min Act: -0.0001

Data Index: 191413 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2838. Min Act: -0.0001

Data Index: 904460 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2634. Min Act: -0.0001

Data Index: 758863 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2775. Min Act: -0.0001

Data Index: 28658 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2438. Min Act: -0.0001

Data Index: 703912 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2605. Min Act: -0.0001

Data Index: 1123298 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2517. Min Act: -0.0001

Data Index: 310644 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2488. Min Act: -0.0001

Data Index: 371340 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2448. Min Act: -0.0001

Data Index: 1019977 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2440. Min Act: -0.0001

Data Index: 1117911 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2627. Min Act: -0.0001

Data Index: 949881 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2531. Min Act: -0.0001

Data Index: 1129101 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2419. Min Act: -0.0001

Data Index: 503517 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2595. Min Act: -0.0001

Data Index: 992595 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2491. Min Act: -0.0001

Data Index: 992524 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2407. Min Act: -0.0001

Data Index: 967859 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2592. Min Act: -0.0001

Data Index: 590968 (C4 (Web Text))

Max Activating Token Index: 492