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

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

Neuron 5302 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6599. Min Range: -3.6599

Max Act: 3.6599. Min Act: -0.0000

Data Index: 902129 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 3.6599. Min Range: -3.6599

Max Act: 3.4575. Min Act: -0.0000

Data Index: 646726 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 3.6599. Min Range: -3.6599

Max Act: 2.6637. Min Act: -0.0000

Data Index: 651016 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 3.6599. Min Range: -3.6599

Max Act: 2.2210. Min Act: -0.0000

Data Index: 8545 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 3.6599. Min Range: -3.6599

Max Act: 2.0672. Min Act: -0.0000

Data Index: 176066 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 3.6599. Min Range: -3.6599

Max Act: 2.0370. Min Act: -0.0000

Data Index: 1323398 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 3.6599. Min Range: -3.6599

Max Act: 2.0188. Min Act: -0.0000

Data Index: 486234 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 3.6599. Min Range: -3.6599

Max Act: 1.9692. Min Act: -0.0000

Data Index: 1048303 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 3.6599. Min Range: -3.6599

Max Act: 1.9626. Min Act: -0.0000

Data Index: 591591 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 3.6599. Min Range: -3.6599

Max Act: 1.9266. Min Act: -0.0000

Data Index: 897874 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 3.6599. Min Range: -3.6599

Max Act: 1.8003. Min Act: -0.0000

Data Index: 719097 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 3.6599. Min Range: -3.6599

Max Act: 1.8589. Min Act: -0.0000

Data Index: 39715 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 3.6599. Min Range: -3.6599

Max Act: 1.7524. Min Act: -0.0000

Data Index: 891553 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 3.6599. Min Range: -3.6599

Max Act: 1.7943. Min Act: -0.0000

Data Index: 465651 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 3.6599. Min Range: -3.6599

Max Act: 1.7960. Min Act: -0.0000

Data Index: 702995 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 3.6599. Min Range: -3.6599

Max Act: 1.7759. Min Act: -0.0000

Data Index: 1507565 (Python Code)

Max Activating Token Index: 505

Text #16

Max Range: 3.6599. Min Range: -3.6599

Max Act: 1.7873. Min Act: -0.0000

Data Index: 1287159 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 3.6599. Min Range: -3.6599

Max Act: 1.7784. Min Act: -0.0000

Data Index: 1176490 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 3.6599. Min Range: -3.6599

Max Act: 1.7760. Min Act: -0.0000

Data Index: 419586 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 3.6599. Min Range: -3.6599

Max Act: 1.8440. Min Act: -0.0000

Data Index: 1090907 (C4 (Web Text))

Max Activating Token Index: 494