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

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

Neuron 4056 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0951. Min Range: -1.0951

Max Act: 1.0951. Min Act: -0.0000

Data Index: 1297341 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 1.0951. Min Range: -1.0951

Max Act: 1.0685. Min Act: -0.0000

Data Index: 425275 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 1.0951. Min Range: -1.0951

Max Act: 1.0632. Min Act: -0.0000

Data Index: 514327 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 1.0951. Min Range: -1.0951

Max Act: 1.0561. Min Act: -0.0000

Data Index: 214542 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9981. Min Act: -0.0000

Data Index: 974147 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 1.0951. Min Range: -1.0951

Max Act: 1.0553. Min Act: -0.0000

Data Index: 1064995 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 1.0951. Min Range: -1.0951

Max Act: 1.0549. Min Act: -0.0000

Data Index: 385558 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9049. Min Act: -0.0000

Data Index: 259767 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9894. Min Act: -0.0000

Data Index: 511378 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9830. Min Act: -0.0000

Data Index: 1285428 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.8466. Min Act: -0.0000

Data Index: 869 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.8814. Min Act: -0.0000

Data Index: 872530 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9357. Min Act: -0.0000

Data Index: 906805 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.8696. Min Act: -0.0000

Data Index: 1232529 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9156. Min Act: -0.0000

Data Index: 166002 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.8065. Min Act: -0.0000

Data Index: 619929 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.8192. Min Act: -0.0000

Data Index: 343564 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.7691. Min Act: -0.0000

Data Index: 608264 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1149454 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.7621. Min Act: -0.0000

Data Index: 221400 (C4 (Web Text))

Max Activating Token Index: 668