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

Dataset: The Pile

Neuron 1843 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2726. Min Range: -1.2726

Max Act: 1.2726. Min Act: -0.0000

Data Index: 355366 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 1.2726. Min Range: -1.2726

Max Act: 1.2043. Min Act: -0.0000

Data Index: 1880876 (The Pile)

Max Activating Token Index: 918

Text #2

Max Range: 1.2726. Min Range: -1.2726

Max Act: 1.0352. Min Act: -0.0000

Data Index: 988207 (The Pile)

Max Activating Token Index: 415

Text #3

Max Range: 1.2726. Min Range: -1.2726

Max Act: 1.0503. Min Act: -0.0000

Data Index: 1830380 (The Pile)

Max Activating Token Index: 975

Text #4

Max Range: 1.2726. Min Range: -1.2726

Max Act: 1.0694. Min Act: -0.0000

Data Index: 335006 (The Pile)

Max Activating Token Index: 983

Text #5

Max Range: 1.2726. Min Range: -1.2726

Max Act: 1.0737. Min Act: -0.0000

Data Index: 711227 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 1.2726. Min Range: -1.2726

Max Act: 1.0462. Min Act: -0.0000

Data Index: 1143120 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 1.2726. Min Range: -1.2726

Max Act: 1.0635. Min Act: -0.0000

Data Index: 238557 (The Pile)

Max Activating Token Index: 1002

Text #8

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.9968. Min Act: -0.0000

Data Index: 1550924 (The Pile)

Max Activating Token Index: 822

Text #9

Max Range: 1.2726. Min Range: -1.2726

Max Act: 1.0651. Min Act: -0.0000

Data Index: 1796331 (The Pile)

Max Activating Token Index: 710

Text #10

Max Range: 1.2726. Min Range: -1.2726

Max Act: 1.1388. Min Act: -0.0000

Data Index: 1723382 (The Pile)

Max Activating Token Index: 184

Text #11

Max Range: 1.2726. Min Range: -1.2726

Max Act: 1.0269. Min Act: -0.0000

Data Index: 919230 (The Pile)

Max Activating Token Index: 655

Text #12

Max Range: 1.2726. Min Range: -1.2726

Max Act: 1.0191. Min Act: -0.0000

Data Index: 697859 (The Pile)

Max Activating Token Index: 972

Text #13

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.9905. Min Act: -0.0000

Data Index: 301177 (The Pile)

Max Activating Token Index: 295

Text #14

Max Range: 1.2726. Min Range: -1.2726

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1379227 (The Pile)

Max Activating Token Index: 486

Text #15

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.8859. Min Act: -0.0000

Data Index: 1385636 (The Pile)

Max Activating Token Index: 797

Text #16

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.9711. Min Act: -0.0000

Data Index: 193970 (The Pile)

Max Activating Token Index: 264

Text #17

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.9071. Min Act: -0.0000

Data Index: 173105 (The Pile)

Max Activating Token Index: 816

Text #18

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.9659. Min Act: -0.0000

Data Index: 719302 (The Pile)

Max Activating Token Index: 757

Text #19

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.9099. Min Act: -0.0000

Data Index: 1939572 (The Pile)

Max Activating Token Index: 966