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

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

Neuron 3080 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: 0.2657. Min Range: -0.2657

Max Act: 0.2573. Min Act: -0.0000

Data Index: 640969 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2657. Min Act: -0.0000

Data Index: 1086976 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1042164 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2446. Min Act: -0.0000

Data Index: 246707 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2372. Min Act: -0.0000

Data Index: 990414 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2352. Min Act: -0.0000

Data Index: 68669 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2268. Min Act: -0.0000

Data Index: 362465 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1265436 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2461. Min Act: -0.0000

Data Index: 745195 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2325. Min Act: -0.0000

Data Index: 768743 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2148. Min Act: -0.0000

Data Index: 616758 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2135. Min Act: -0.0000

Data Index: 204883 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2002. Min Act: -0.0000

Data Index: 205484 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1999. Min Act: -0.0000

Data Index: 561475 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2142. Min Act: -0.0000

Data Index: 706385 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1205920 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1089496 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2126. Min Act: -0.0000

Data Index: 129956 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1907. Min Act: -0.0000

Data Index: 1297325 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2026. Min Act: -0.0000

Data Index: 426444 (C4 (Web Text))

Max Activating Token Index: 72