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

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

Neuron 1745 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: 1.4730. Min Range: -1.4730

Max Act: 1.4730. Min Act: -0.0001

Data Index: 717554 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.1886. Min Act: -0.0001

Data Index: 1024696 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.3190. Min Act: -0.0001

Data Index: 203206 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2960. Min Act: -0.0001

Data Index: 328258 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2442. Min Act: -0.0001

Data Index: 845189 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2022. Min Act: -0.0001

Data Index: 1172193 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.1349. Min Act: -0.0001

Data Index: 414538 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0342. Min Act: -0.0001

Data Index: 1005218 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.1305. Min Act: -0.0001

Data Index: 180955 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0786. Min Act: -0.0001

Data Index: 236918 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 1.4730. Min Range: -1.4730

Max Act: 0.8545. Min Act: -0.0001

Data Index: 604364 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 1.4730. Min Range: -1.4730

Max Act: 0.9247. Min Act: -0.0001

Data Index: 376860 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 1.4730. Min Range: -1.4730

Max Act: 0.9052. Min Act: -0.0001

Data Index: 293817 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 1.4730. Min Range: -1.4730

Max Act: 0.8719. Min Act: -0.0001

Data Index: 382439 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 1.4730. Min Range: -1.4730

Max Act: 0.9230. Min Act: -0.0001

Data Index: 346838 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 1.4730. Min Range: -1.4730

Max Act: 0.8839. Min Act: -0.0001

Data Index: 156474 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 1.4730. Min Range: -1.4730

Max Act: 0.9195. Min Act: -0.0001

Data Index: 415562 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 1.4730. Min Range: -1.4730

Max Act: 0.8857. Min Act: -0.0001

Data Index: 1228871 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 1.4730. Min Range: -1.4730

Max Act: 0.8530. Min Act: -0.0001

Data Index: 651699 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 1.4730. Min Range: -1.4730

Max Act: 0.9329. Min Act: -0.0001

Data Index: 1103887 (C4 (Web Text))

Max Activating Token Index: 160