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

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

Neuron 3771 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6776. Min Act: -0.0000

Data Index: 564581 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6937. Min Act: -0.0000

Data Index: 494643 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1313973 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6765. Min Act: -0.0000

Data Index: 980675 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1131249 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5911. Min Act: -0.0000

Data Index: 265557 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5669. Min Act: -0.0000

Data Index: 1182114 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5186. Min Act: -0.0000

Data Index: 1318830 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5444. Min Act: -0.0000

Data Index: 834243 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4914. Min Act: -0.0000

Data Index: 167883 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5095. Min Act: -0.0000

Data Index: 396986 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5451. Min Act: -0.0000

Data Index: 841702 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5042. Min Act: -0.0000

Data Index: 729436 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4694. Min Act: -0.0000

Data Index: 460379 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1359149 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4670. Min Act: -0.0000

Data Index: 518491 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4613. Min Act: -0.0000

Data Index: 1262800 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4571. Min Act: -0.0000

Data Index: 402162 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4886. Min Act: -0.0000

Data Index: 267991 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4435. Min Act: -0.0000

Data Index: 676203 (C4 (Web Text))

Max Activating Token Index: 60