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

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

Neuron 5506 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0053. Min Range: -2.0053

Max Act: 2.0053. Min Act: -0.0000

Data Index: 690520 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 2.0053. Min Range: -2.0053

Max Act: 1.9231. Min Act: -0.0000

Data Index: 904130 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 2.0053. Min Range: -2.0053

Max Act: 1.6347. Min Act: -0.0000

Data Index: 1083024 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 2.0053. Min Range: -2.0053

Max Act: 1.8984. Min Act: -0.0000

Data Index: 1204800 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 2.0053. Min Range: -2.0053

Max Act: 1.6940. Min Act: -0.0000

Data Index: 380999 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 2.0053. Min Range: -2.0053

Max Act: 1.7324. Min Act: -0.0000

Data Index: 1241352 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 2.0053. Min Range: -2.0053

Max Act: 1.7069. Min Act: -0.0000

Data Index: 181871 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 2.0053. Min Range: -2.0053

Max Act: 1.6641. Min Act: -0.0000

Data Index: 807581 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 2.0053. Min Range: -2.0053

Max Act: 1.7618. Min Act: -0.0000

Data Index: 1262055 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 2.0053. Min Range: -2.0053

Max Act: 1.6548. Min Act: -0.0000

Data Index: 924526 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 2.0053. Min Range: -2.0053

Max Act: 1.5124. Min Act: -0.0000

Data Index: 912430 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 2.0053. Min Range: -2.0053

Max Act: 1.5422. Min Act: -0.0000

Data Index: 911309 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 2.0053. Min Range: -2.0053

Max Act: 1.5859. Min Act: -0.0000

Data Index: 4036 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 2.0053. Min Range: -2.0053

Max Act: 1.5582. Min Act: -0.0000

Data Index: 16000 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 2.0053. Min Range: -2.0053

Max Act: 1.5437. Min Act: -0.0000

Data Index: 214809 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 2.0053. Min Range: -2.0053

Max Act: 1.7381. Min Act: -0.0000

Data Index: 1321450 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 2.0053. Min Range: -2.0053

Max Act: 1.6124. Min Act: -0.0000

Data Index: 1110418 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 2.0053. Min Range: -2.0053

Max Act: 1.4284. Min Act: -0.0000

Data Index: 469146 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 2.0053. Min Range: -2.0053

Max Act: 1.4177. Min Act: -0.0000

Data Index: 310786 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 2.0053. Min Range: -2.0053

Max Act: 1.5746. Min Act: -0.0000

Data Index: 261246 (C4 (Web Text))

Max Activating Token Index: 19