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

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

Neuron 4217 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: 0.3236. Min Range: -0.3236

Max Act: 0.3236. Min Act: -0.0000

Data Index: 193136 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2815. Min Act: -0.0000

Data Index: 139526 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2626. Min Act: -0.0000

Data Index: 69303 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2589. Min Act: -0.0000

Data Index: 132693 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1263510 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1256127 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2246. Min Act: -0.0000

Data Index: 929691 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2208. Min Act: -0.0000

Data Index: 1170050 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1200500 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2127. Min Act: -0.0000

Data Index: 714657 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2064. Min Act: -0.0000

Data Index: 549417 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2082. Min Act: -0.0000

Data Index: 587073 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1236809 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2063. Min Act: -0.0000

Data Index: 747375 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2004. Min Act: -0.0000

Data Index: 987520 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.1996. Min Act: -0.0000

Data Index: 800363 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.1926. Min Act: -0.0000

Data Index: 1108016 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2003. Min Act: -0.0000

Data Index: 912588 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1127044 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.1936. Min Act: -0.0000

Data Index: 281790 (C4 (Web Text))

Max Activating Token Index: 550