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

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

Neuron 3235 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0851. Min Act: -0.0000

Data Index: 940173 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0769. Min Act: -0.0001

Data Index: 1222979 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0770. Min Act: -0.0000

Data Index: 1187446 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1267033 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0759. Min Act: -0.0000

Data Index: 336560 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0732. Min Act: -0.0000

Data Index: 339823 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0767. Min Act: -0.0000

Data Index: 1309342 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1161002 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0759. Min Act: -0.0001

Data Index: 531602 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0681. Min Act: -0.0000

Data Index: 1289752 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1629738 (Python Code)

Max Activating Token Index: 732

Text #11

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0677. Min Act: -0.0001

Data Index: 1285973 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0649. Min Act: -0.0000

Data Index: 599459 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0672. Min Act: -0.0000

Data Index: 1323310 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0651. Min Act: -0.0001

Data Index: 1433834 (Python Code)

Max Activating Token Index: 513

Text #15

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0716. Min Act: -0.0000

Data Index: 263842 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0701. Min Act: -0.0000

Data Index: 1025254 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0650. Min Act: -0.0001

Data Index: 593049 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0649. Min Act: -0.0000

Data Index: 782704 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0664. Min Act: -0.0000

Data Index: 624138 (C4 (Web Text))

Max Activating Token Index: 535