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

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

Neuron 1782 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: 0.2907. Min Range: -0.2907

Max Act: 0.2907. Min Act: -0.0001

Data Index: 870666 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2455. Min Act: -0.0001

Data Index: 1019968 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2761. Min Act: -0.0001

Data Index: 375562 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2665. Min Act: -0.0001

Data Index: 1137134 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2810. Min Act: -0.0001

Data Index: 640991 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2802. Min Act: -0.0001

Data Index: 374324 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2566. Min Act: -0.0001

Data Index: 696741 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2764. Min Act: -0.0001

Data Index: 783072 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2621. Min Act: -0.0001

Data Index: 218296 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2732. Min Act: -0.0001

Data Index: 767232 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2769. Min Act: -0.0001

Data Index: 974575 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2756. Min Act: -0.0001

Data Index: 1119598 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2487. Min Act: -0.0001

Data Index: 1029880 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2721. Min Act: -0.0001

Data Index: 1083753 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2633. Min Act: -0.0001

Data Index: 1116556 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2726. Min Act: -0.0001

Data Index: 1264428 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2450. Min Act: -0.0001

Data Index: 555561 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2441. Min Act: -0.0001

Data Index: 889490 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2537. Min Act: -0.0001

Data Index: 818066 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2620. Min Act: -0.0001

Data Index: 1020443 (C4 (Web Text))

Max Activating Token Index: 88