Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4176 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.5690. Min Act: -0.0000

Data Index: 894084 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.5314. Min Act: -0.0000

Data Index: 620096 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.5753. Min Act: -0.0000

Data Index: 408611 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.2968. Min Act: -0.0000

Data Index: 959503 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.3644. Min Act: -0.0000

Data Index: 1163853 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.3889. Min Act: -0.0000

Data Index: 1167929 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.3152. Min Act: -0.0000

Data Index: 318051 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.3810. Min Act: -0.0000

Data Index: 679371 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.2682. Min Act: -0.0000

Data Index: 478187 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.2794. Min Act: -0.0000

Data Index: 145514 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.1519. Min Act: -0.0000

Data Index: 711171 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.2642. Min Act: -0.0000

Data Index: 1033630 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.2261. Min Act: -0.0000

Data Index: 883663 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.2526. Min Act: -0.0000

Data Index: 1105629 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.2379. Min Act: -0.0000

Data Index: 903248 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.2288. Min Act: -0.0000

Data Index: 993472 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.2981. Min Act: -0.0000

Data Index: 480597 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.2063. Min Act: -0.0000

Data Index: 109909 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.2060. Min Act: -0.0000

Data Index: 56613 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 1.5753. Min Range: -1.5753

Max Act: 1.1703. Min Act: -0.0000

Data Index: 1095727 (C4 (Web Text))

Max Activating Token Index: 593