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

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

Neuron 271 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4824. Min Act: -0.0001

Data Index: 61923 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3511. Min Act: -0.0001

Data Index: 283709 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3523. Min Act: -0.0001

Data Index: 40504 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3628. Min Act: -0.0001

Data Index: 975442 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3189. Min Act: -0.0001

Data Index: 1105172 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3190. Min Act: -0.0001

Data Index: 1283001 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3297. Min Act: -0.0001

Data Index: 920986 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3253. Min Act: -0.0001

Data Index: 976582 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.2957. Min Act: -0.0001

Data Index: 318283 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.2983. Min Act: -0.0001

Data Index: 363156 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3325. Min Act: -0.0001

Data Index: 1129650 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3068. Min Act: -0.0001

Data Index: 577256 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3046. Min Act: -0.0001

Data Index: 775483 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.2990. Min Act: -0.0001

Data Index: 633503 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.2986. Min Act: -0.0001

Data Index: 569043 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3063. Min Act: -0.0001

Data Index: 1140456 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.2835. Min Act: -0.0001

Data Index: 603659 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.2838. Min Act: -0.0001

Data Index: 1042767 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3019. Min Act: -0.0001

Data Index: 119671 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.2391. Min Act: -0.0001

Data Index: 263338 (C4 (Web Text))

Max Activating Token Index: 567