Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 292 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.4708. Min Act: -0.0001

Data Index: 398784 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.4650. Min Act: -0.0001

Data Index: 1155969 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.4104. Min Act: -0.0001

Data Index: 153596 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.3667. Min Act: -0.0001

Data Index: 544605 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.3619. Min Act: -0.0001

Data Index: 76574 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.3409. Min Act: -0.0001

Data Index: 458518 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.3278. Min Act: -0.0001

Data Index: 1247021 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.3035. Min Act: -0.0001

Data Index: 1319588 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2983. Min Act: -0.0001

Data Index: 128545 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.3114. Min Act: -0.0001

Data Index: 484713 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.3064. Min Act: -0.0001

Data Index: 1029461 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2678. Min Act: -0.0001

Data Index: 920381 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2902. Min Act: -0.0001

Data Index: 810113 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2790. Min Act: -0.0001

Data Index: 818731 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2734. Min Act: -0.0001

Data Index: 295724 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2781. Min Act: -0.0001

Data Index: 928293 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2484. Min Act: -0.0001

Data Index: 1137156 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2633. Min Act: -0.0001

Data Index: 513571 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2556. Min Act: -0.0001

Data Index: 13126 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2698. Min Act: -0.0001

Data Index: 384087 (C4 (Web Text))

Max Activating Token Index: 947