Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5028 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.6022. Min Act: -0.0000

Data Index: 217587 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.6229. Min Act: -0.0000

Data Index: 64577 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5966. Min Act: -0.0001

Data Index: 963944 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5024. Min Act: -0.0000

Data Index: 124092 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4980. Min Act: -0.0000

Data Index: 1023563 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4503. Min Act: -0.0000

Data Index: 157523 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4316. Min Act: -0.0000

Data Index: 1249709 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4631. Min Act: -0.0001

Data Index: 564323 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5072. Min Act: -0.0000

Data Index: 652983 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1217735 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1181311 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4550. Min Act: -0.0000

Data Index: 776689 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4784. Min Act: -0.0000

Data Index: 868156 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4942. Min Act: -0.0000

Data Index: 798529 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4725. Min Act: -0.0000

Data Index: 1201965 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4828. Min Act: -0.0000

Data Index: 976113 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4329. Min Act: -0.0000

Data Index: 403485 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4466. Min Act: -0.0000

Data Index: 439243 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4826. Min Act: -0.0000

Data Index: 971603 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4661. Min Act: -0.0000

Data Index: 934662 (C4 (Web Text))

Max Activating Token Index: 308