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

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

Neuron 1299 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: 2.4051. Min Range: -2.4051

Max Act: 2.4051. Min Act: -0.0000

Data Index: 599392 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 2.4051. Min Range: -2.4051

Max Act: 2.2517. Min Act: -0.0000

Data Index: 1040791 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 2.4051. Min Range: -2.4051

Max Act: 1.6820. Min Act: -0.0000

Data Index: 899505 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 2.4051. Min Range: -2.4051

Max Act: 1.6676. Min Act: -0.0000

Data Index: 26255 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 2.4051. Min Range: -2.4051

Max Act: 1.6403. Min Act: -0.0000

Data Index: 784932 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 2.4051. Min Range: -2.4051

Max Act: 1.5174. Min Act: -0.0000

Data Index: 15956 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 2.4051. Min Range: -2.4051

Max Act: 1.6859. Min Act: -0.0000

Data Index: 582766 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 2.4051. Min Range: -2.4051

Max Act: 1.3909. Min Act: -0.0000

Data Index: 366001 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 2.4051. Min Range: -2.4051

Max Act: 1.6483. Min Act: -0.0000

Data Index: 86090 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 2.4051. Min Range: -2.4051

Max Act: 1.5323. Min Act: -0.0000

Data Index: 651562 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 2.4051. Min Range: -2.4051

Max Act: 1.6104. Min Act: -0.0000

Data Index: 964684 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 2.4051. Min Range: -2.4051

Max Act: 1.4218. Min Act: -0.0000

Data Index: 762699 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 2.4051. Min Range: -2.4051

Max Act: 1.4936. Min Act: -0.0000

Data Index: 447706 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 2.4051. Min Range: -2.4051

Max Act: 1.3990. Min Act: -0.0000

Data Index: 861219 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 2.4051. Min Range: -2.4051

Max Act: 1.5622. Min Act: -0.0000

Data Index: 650483 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 2.4051. Min Range: -2.4051

Max Act: 1.4566. Min Act: -0.0000

Data Index: 417265 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 2.4051. Min Range: -2.4051

Max Act: 1.4577. Min Act: -0.0000

Data Index: 168966 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 2.4051. Min Range: -2.4051

Max Act: 1.3627. Min Act: -0.0000

Data Index: 1208762 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 2.4051. Min Range: -2.4051

Max Act: 1.4565. Min Act: -0.0000

Data Index: 1271173 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 2.4051. Min Range: -2.4051

Max Act: 1.5368. Min Act: -0.0000

Data Index: 108077 (C4 (Web Text))

Max Activating Token Index: 283