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

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

Neuron 4450 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.6633. Min Act: -0.0000

Data Index: 1001597 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.6390. Min Act: -0.0000

Data Index: 242036 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.6160. Min Act: -0.0000

Data Index: 483241 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.6099. Min Act: -0.0000

Data Index: 604758 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1355137 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.5798. Min Act: -0.0000

Data Index: 263688 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1008065 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.5514. Min Act: 0.0000

Data Index: 1188536 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.5161. Min Act: -0.0000

Data Index: 414490 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.5305. Min Act: -0.0000

Data Index: 600349 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.5528. Min Act: -0.0000

Data Index: 883888 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.5204. Min Act: -0.0000

Data Index: 820918 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.5033. Min Act: -0.0000

Data Index: 635423 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.5330. Min Act: -0.0000

Data Index: 336754 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.4645. Min Act: -0.0000

Data Index: 187729 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.4987. Min Act: -0.0000

Data Index: 517268 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.4789. Min Act: -0.0000

Data Index: 1009090 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.4772. Min Act: -0.0000

Data Index: 165869 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1301132 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1070976 (C4 (Web Text))

Max Activating Token Index: 287