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

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

Neuron 58 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.6363. Min Act: -0.0001

Data Index: 650798 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5542. Min Act: -0.0001

Data Index: 971674 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5086. Min Act: -0.0001

Data Index: 1312662 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5412. Min Act: -0.0001

Data Index: 1359775 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5202. Min Act: -0.0001

Data Index: 1048934 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4778. Min Act: -0.0001

Data Index: 264001 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4778. Min Act: -0.0001

Data Index: 415044 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5089. Min Act: -0.0001

Data Index: 1174865 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5020. Min Act: -0.0001

Data Index: 325664 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4970. Min Act: -0.0001

Data Index: 190802 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4629. Min Act: -0.0001

Data Index: 1272309 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5210. Min Act: -0.0001

Data Index: 872298 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4883. Min Act: -0.0001

Data Index: 341445 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4898. Min Act: -0.0001

Data Index: 625275 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4815. Min Act: -0.0001

Data Index: 142800 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4497. Min Act: -0.0001

Data Index: 1063218 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4463. Min Act: -0.0001

Data Index: 906832 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4623. Min Act: -0.0001

Data Index: 212585 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4925. Min Act: -0.0001

Data Index: 742491 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4887. Min Act: -0.0001

Data Index: 346307 (C4 (Web Text))

Max Activating Token Index: 41