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

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

Neuron 1072 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.5808. Min Act: -0.0001

Data Index: 705148 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.5247. Min Act: -0.0002

Data Index: 1189371 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.5127. Min Act: -0.0001

Data Index: 80328 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.5194. Min Act: -0.0001

Data Index: 297351 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.5207. Min Act: -0.0002

Data Index: 739757 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.5238. Min Act: -0.0001

Data Index: 412788 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.5154. Min Act: -0.0001

Data Index: 1090072 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.5114. Min Act: -0.0001

Data Index: 551579 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.5246. Min Act: -0.0002

Data Index: 587440 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.5085. Min Act: -0.0002

Data Index: 595048 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.4981. Min Act: -0.0001

Data Index: 568812 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.5058. Min Act: -0.0002

Data Index: 1332249 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.4908. Min Act: -0.0001

Data Index: 843 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.4920. Min Act: -0.0001

Data Index: 35489 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.4914. Min Act: -0.0002

Data Index: 318654 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.4771. Min Act: -0.0002

Data Index: 1071900 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.4796. Min Act: -0.0001

Data Index: 801468 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.4880. Min Act: -0.0002

Data Index: 863662 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.4777. Min Act: -0.0001

Data Index: 1042282 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.5808. Min Range: -0.5808

Max Act: 0.4388. Min Act: -0.0002

Data Index: 645885 (C4 (Web Text))

Max Activating Token Index: 332