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

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

Neuron 6057 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: 1.9798. Min Range: -1.9798

Max Act: 1.9798. Min Act: -0.0001

Data Index: 414022 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 1.9798. Min Range: -1.9798

Max Act: 1.6495. Min Act: -0.0001

Data Index: 754809 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 1.9798. Min Range: -1.9798

Max Act: 1.7878. Min Act: -0.0000

Data Index: 469085 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 1.9798. Min Range: -1.9798

Max Act: 1.5785. Min Act: -0.0001

Data Index: 440345 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 1.9798. Min Range: -1.9798

Max Act: 1.5127. Min Act: -0.0001

Data Index: 1076736 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 1.9798. Min Range: -1.9798

Max Act: 1.5453. Min Act: -0.0000

Data Index: 163046 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 1.9798. Min Range: -1.9798

Max Act: 1.4985. Min Act: -0.0001

Data Index: 1296617 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 1.9798. Min Range: -1.9798

Max Act: 1.4886. Min Act: -0.0001

Data Index: 223730 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 1.9798. Min Range: -1.9798

Max Act: 1.3421. Min Act: -0.0000

Data Index: 1038031 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 1.9798. Min Range: -1.9798

Max Act: 1.3862. Min Act: -0.0001

Data Index: 731953 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 1.9798. Min Range: -1.9798

Max Act: 1.3669. Min Act: -0.0001

Data Index: 588073 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 1.9798. Min Range: -1.9798

Max Act: 1.5883. Min Act: -0.0000

Data Index: 647620 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 1.9798. Min Range: -1.9798

Max Act: 1.3943. Min Act: -0.0001

Data Index: 628812 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 1.9798. Min Range: -1.9798

Max Act: 1.3683. Min Act: -0.0001

Data Index: 554874 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 1.9798. Min Range: -1.9798

Max Act: 1.2968. Min Act: -0.0000

Data Index: 1143943 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 1.9798. Min Range: -1.9798

Max Act: 1.3472. Min Act: -0.0001

Data Index: 1133310 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 1.9798. Min Range: -1.9798

Max Act: 1.3481. Min Act: -0.0001

Data Index: 344782 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 1.9798. Min Range: -1.9798

Max Act: 1.3217. Min Act: -0.0000

Data Index: 823245 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 1.9798. Min Range: -1.9798

Max Act: 1.2502. Min Act: -0.0000

Data Index: 993634 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 1.9798. Min Range: -1.9798

Max Act: 1.3563. Min Act: -0.0001

Data Index: 699332 (C4 (Web Text))

Max Activating Token Index: 911