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

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

Neuron 3235 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8681. Min Range: -3.8681

Max Act: 3.8681. Min Act: -0.0000

Data Index: 1278702 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 3.8681. Min Range: -3.8681

Max Act: 3.4952. Min Act: -0.0000

Data Index: 1063251 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 3.8681. Min Range: -3.8681

Max Act: 3.4745. Min Act: -0.0000

Data Index: 1043497 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 3.8681. Min Range: -3.8681

Max Act: 3.2303. Min Act: -0.0000

Data Index: 405945 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 3.8681. Min Range: -3.8681

Max Act: 3.4361. Min Act: -0.0000

Data Index: 1236402 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 3.8681. Min Range: -3.8681

Max Act: 3.0866. Min Act: -0.0000

Data Index: 553700 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 3.8681. Min Range: -3.8681

Max Act: 3.2330. Min Act: -0.0000

Data Index: 352738 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 3.8681. Min Range: -3.8681

Max Act: 3.5142. Min Act: -0.0000

Data Index: 1245705 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 3.8681. Min Range: -3.8681

Max Act: 3.0784. Min Act: -0.0000

Data Index: 592740 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 3.8681. Min Range: -3.8681

Max Act: 2.8955. Min Act: -0.0000

Data Index: 1108697 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 3.8681. Min Range: -3.8681

Max Act: 2.9582. Min Act: -0.0000

Data Index: 477041 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 3.8681. Min Range: -3.8681

Max Act: 3.0583. Min Act: -0.0000

Data Index: 414619 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 3.8681. Min Range: -3.8681

Max Act: 2.9029. Min Act: -0.0000

Data Index: 901705 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 3.8681. Min Range: -3.8681

Max Act: 2.8253. Min Act: -0.0000

Data Index: 710393 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 3.8681. Min Range: -3.8681

Max Act: 2.6756. Min Act: -0.0000

Data Index: 56076 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 3.8681. Min Range: -3.8681

Max Act: 2.7662. Min Act: -0.0000

Data Index: 157391 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 3.8681. Min Range: -3.8681

Max Act: 2.7685. Min Act: -0.0000

Data Index: 229761 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 3.8681. Min Range: -3.8681

Max Act: 2.6131. Min Act: -0.0000

Data Index: 365298 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 3.8681. Min Range: -3.8681

Max Act: 2.8713. Min Act: -0.0000

Data Index: 125459 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 3.8681. Min Range: -3.8681

Max Act: 2.7330. Min Act: -0.0000

Data Index: 1299073 (C4 (Web Text))

Max Activating Token Index: 643