Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 787 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0912. Min Act: -0.0004

Data Index: 161986 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0873. Min Act: -0.0003

Data Index: 1115223 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0969. Min Act: -0.0003

Data Index: 1178527 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.1026. Min Act: -0.0003

Data Index: 653460 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0869. Min Act: -0.0003

Data Index: 412043 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0903. Min Act: -0.0003

Data Index: 709537 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0837. Min Act: -0.0003

Data Index: 627951 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0937. Min Act: -0.0003

Data Index: 576349 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0983. Min Act: -0.0003

Data Index: 346586 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0914. Min Act: -0.0003

Data Index: 364486 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0907. Min Act: -0.0003

Data Index: 399347 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0973. Min Act: -0.0003

Data Index: 1098769 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0864. Min Act: -0.0003

Data Index: 193171 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0823. Min Act: -0.0003

Data Index: 684376 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0836. Min Act: -0.0003

Data Index: 381174 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0869. Min Act: -0.0003

Data Index: 269106 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0808. Min Act: -0.0003

Data Index: 507047 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0775. Min Act: -0.0003

Data Index: 74223 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0937. Min Act: -0.0003

Data Index: 1310511 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0902. Min Act: -0.0003

Data Index: 682349 (C4 (Web Text))

Max Activating Token Index: 692