Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2444 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3512. Min Act: -0.0001

Data Index: 463704 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3496. Min Act: -0.0001

Data Index: 892862 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3109. Min Act: -0.0001

Data Index: 1325766 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3010. Min Act: -0.0001

Data Index: 513041 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3332. Min Act: -0.0001

Data Index: 310287 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3135. Min Act: -0.0001

Data Index: 817832 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2907. Min Act: -0.0001

Data Index: 146162 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3093. Min Act: -0.0001

Data Index: 992650 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2756. Min Act: -0.0001

Data Index: 1120564 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2745. Min Act: -0.0001

Data Index: 612386 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2961. Min Act: -0.0001

Data Index: 226767 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2472. Min Act: -0.0001

Data Index: 1015378 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2952. Min Act: -0.0001

Data Index: 821546 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2873. Min Act: -0.0001

Data Index: 46796 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2839. Min Act: -0.0001

Data Index: 1316113 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2797. Min Act: -0.0001

Data Index: 333546 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.3139. Min Act: -0.0001

Data Index: 277706 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2931. Min Act: -0.0001

Data Index: 623229 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2858. Min Act: -0.0001

Data Index: 364232 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.3512. Min Range: -0.3512

Max Act: 0.2847. Min Act: -0.0001

Data Index: 6057 (C4 (Web Text))

Max Activating Token Index: 850