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

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

Neuron 4579 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: 2.2922. Min Range: -2.2922

Max Act: 2.2922. Min Act: -0.0001

Data Index: 257690 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 2.2922. Min Range: -2.2922

Max Act: 2.2050. Min Act: -0.0001

Data Index: 59199 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 2.2922. Min Range: -2.2922

Max Act: 2.1582. Min Act: -0.0000

Data Index: 608530 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 2.2922. Min Range: -2.2922

Max Act: 1.9430. Min Act: -0.0001

Data Index: 51319 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 2.2922. Min Range: -2.2922

Max Act: 1.9345. Min Act: -0.0001

Data Index: 602300 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 2.2922. Min Range: -2.2922

Max Act: 1.7817. Min Act: -0.0001

Data Index: 1132753 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 2.2922. Min Range: -2.2922

Max Act: 1.9761. Min Act: -0.0000

Data Index: 391169 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 2.2922. Min Range: -2.2922

Max Act: 1.9301. Min Act: -0.0000

Data Index: 1124566 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 2.2922. Min Range: -2.2922

Max Act: 1.9958. Min Act: -0.0000

Data Index: 736172 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 2.2922. Min Range: -2.2922

Max Act: 1.4952. Min Act: -0.0000

Data Index: 1337158 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 2.2922. Min Range: -2.2922

Max Act: 1.9694. Min Act: -0.0001

Data Index: 2994 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 2.2922. Min Range: -2.2922

Max Act: 1.9600. Min Act: -0.0001

Data Index: 806903 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 2.2922. Min Range: -2.2922

Max Act: 1.7642. Min Act: -0.0001

Data Index: 1241934 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 2.2922. Min Range: -2.2922

Max Act: 1.7857. Min Act: -0.0000

Data Index: 385904 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 2.2922. Min Range: -2.2922

Max Act: 1.9000. Min Act: -0.0000

Data Index: 334271 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 2.2922. Min Range: -2.2922

Max Act: 1.8487. Min Act: -0.0001

Data Index: 1057987 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 2.2922. Min Range: -2.2922

Max Act: 1.7683. Min Act: -0.0001

Data Index: 142529 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 2.2922. Min Range: -2.2922

Max Act: 1.8514. Min Act: -0.0000

Data Index: 451077 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 2.2922. Min Range: -2.2922

Max Act: 1.7663. Min Act: -0.0000

Data Index: 1070495 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 2.2922. Min Range: -2.2922

Max Act: 1.7408. Min Act: -0.0000

Data Index: 927387 (C4 (Web Text))

Max Activating Token Index: 973