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

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

Neuron 2355 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0804. Min Range: -2.0804

Max Act: 1.9814. Min Act: -0.0000

Data Index: 458811 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 2.0804. Min Range: -2.0804

Max Act: 1.7305. Min Act: -0.0000

Data Index: 277398 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 2.0804. Min Range: -2.0804

Max Act: 1.7229. Min Act: -0.0000

Data Index: 552109 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 2.0804. Min Range: -2.0804

Max Act: 1.5766. Min Act: -0.0000

Data Index: 210579 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 2.0804. Min Range: -2.0804

Max Act: 2.0804. Min Act: -0.0000

Data Index: 647718 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 2.0804. Min Range: -2.0804

Max Act: 1.7034. Min Act: -0.0000

Data Index: 695964 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 2.0804. Min Range: -2.0804

Max Act: 1.7891. Min Act: -0.0000

Data Index: 342432 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 2.0804. Min Range: -2.0804

Max Act: 1.6990. Min Act: -0.0000

Data Index: 742603 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 2.0804. Min Range: -2.0804

Max Act: 1.6920. Min Act: -0.0000

Data Index: 1091410 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 2.0804. Min Range: -2.0804

Max Act: 1.6959. Min Act: -0.0000

Data Index: 462169 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 2.0804. Min Range: -2.0804

Max Act: 1.7697. Min Act: -0.0000

Data Index: 848273 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 2.0804. Min Range: -2.0804

Max Act: 1.7498. Min Act: -0.0000

Data Index: 318225 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 2.0804. Min Range: -2.0804

Max Act: 1.6182. Min Act: -0.0000

Data Index: 977579 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 2.0804. Min Range: -2.0804

Max Act: 1.3519. Min Act: -0.0000

Data Index: 770500 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 2.0804. Min Range: -2.0804

Max Act: 1.6859. Min Act: -0.0000

Data Index: 177853 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 2.0804. Min Range: -2.0804

Max Act: 1.3294. Min Act: -0.0000

Data Index: 537759 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 2.0804. Min Range: -2.0804

Max Act: 1.4581. Min Act: -0.0000

Data Index: 28646 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 2.0804. Min Range: -2.0804

Max Act: 1.3197. Min Act: -0.0000

Data Index: 875051 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 2.0804. Min Range: -2.0804

Max Act: 1.4852. Min Act: -0.0000

Data Index: 1119203 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 2.0804. Min Range: -2.0804

Max Act: 1.4898. Min Act: -0.0000

Data Index: 241619 (C4 (Web Text))

Max Activating Token Index: 470