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

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

Neuron 3966 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1259008 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1338576 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4446. Min Act: -0.0001

Data Index: 32355 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4227. Min Act: -0.0001

Data Index: 374771 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4208. Min Act: -0.0000

Data Index: 33422 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1253496 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3772. Min Act: -0.0001

Data Index: 669188 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3596. Min Act: -0.0000

Data Index: 564969 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3949. Min Act: -0.0000

Data Index: 841976 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4088. Min Act: -0.0001

Data Index: 221808 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3680. Min Act: -0.0000

Data Index: 1082410 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1200582 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3903. Min Act: -0.0000

Data Index: 452008 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3722. Min Act: -0.0001

Data Index: 703838 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3835. Min Act: -0.0001

Data Index: 727777 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1355748 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4054. Min Act: -0.0001

Data Index: 346343 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1076496 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3973. Min Act: -0.0000

Data Index: 80965 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3581. Min Act: -0.0000

Data Index: 788691 (C4 (Web Text))

Max Activating Token Index: 992