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

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

Neuron 4874 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.7117. Min Act: -0.0000

Data Index: 160515 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.6985. Min Act: -0.0000

Data Index: 973105 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.6722. Min Act: -0.0000

Data Index: 263991 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.6042. Min Act: -0.0000

Data Index: 788264 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.5877. Min Act: -0.0000

Data Index: 71462 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.5293. Min Act: -0.0000

Data Index: 772528 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.5485. Min Act: 0.0000

Data Index: 901581 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.5119. Min Act: -0.0000

Data Index: 1162915 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4777. Min Act: -0.0000

Data Index: 356833 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4731. Min Act: -0.0000

Data Index: 1016963 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4676. Min Act: -0.0000

Data Index: 693222 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4714. Min Act: -0.0000

Data Index: 398032 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4482. Min Act: 0.0000

Data Index: 344365 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4626. Min Act: -0.0000

Data Index: 418675 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4211. Min Act: -0.0000

Data Index: 108748 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.3965. Min Act: -0.0000

Data Index: 869693 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4151. Min Act: 0.0000

Data Index: 501602 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4159. Min Act: -0.0000

Data Index: 158833 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4227. Min Act: -0.0000

Data Index: 28977 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.4119. Min Act: -0.0000

Data Index: 997682 (C4 (Web Text))

Max Activating Token Index: 633