Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1834 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.5244. Min Act: -0.0000

Data Index: 994988 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.5603. Min Act: -0.0000

Data Index: 1169530 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.4879. Min Act: -0.0000

Data Index: 767067 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.4617. Min Act: -0.0001

Data Index: 1007538 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.4714. Min Act: -0.0001

Data Index: 835939 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.3759. Min Act: -0.0000

Data Index: 1258101 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.3351. Min Act: -0.0001

Data Index: 829580 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.3431. Min Act: -0.0000

Data Index: 820953 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.3634. Min Act: -0.0000

Data Index: 263083 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.2798. Min Act: -0.0000

Data Index: 761195 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.3059. Min Act: -0.0001

Data Index: 802843 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.2550. Min Act: -0.0000

Data Index: 851382 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.1951. Min Act: -0.0000

Data Index: 603445 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.2326. Min Act: -0.0000

Data Index: 821808 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.2132. Min Act: -0.0000

Data Index: 1310130 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.2018. Min Act: -0.0000

Data Index: 698017 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.2030. Min Act: -0.0000

Data Index: 93138 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.0658. Min Act: -0.0001

Data Index: 742554 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.2495. Min Act: -0.0000

Data Index: 408270 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 1.5603. Min Range: -1.5603

Max Act: 1.2226. Min Act: -0.0000

Data Index: 181658 (C4 (Web Text))

Max Activating Token Index: 63