Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 61 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1090. Min Act: -0.0000

Data Index: 635454 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1001. Min Act: -0.0000

Data Index: 651060 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1008. Min Act: -0.0000

Data Index: 1258064 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1020. Min Act: -0.0000

Data Index: 630649 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0900. Min Act: -0.0000

Data Index: 379733 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1024. Min Act: -0.0000

Data Index: 345513 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0898. Min Act: -0.0000

Data Index: 1278466 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0929. Min Act: -0.0001

Data Index: 793360 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1235303 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0886. Min Act: -0.0000

Data Index: 935324 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0835. Min Act: -0.0000

Data Index: 555765 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0822. Min Act: -0.0000

Data Index: 480330 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0822. Min Act: -0.0000

Data Index: 644021 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0883. Min Act: -0.0000

Data Index: 1002315 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0958. Min Act: -0.0000

Data Index: 276165 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0768. Min Act: -0.0000

Data Index: 530213 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0770. Min Act: -0.0000

Data Index: 79478 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0907. Min Act: -0.0000

Data Index: 786480 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0740. Min Act: -0.0000

Data Index: 157157 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0837. Min Act: -0.0000

Data Index: 282005 (C4 (Web Text))

Max Activating Token Index: 200