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

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

Neuron 429 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6908. Min Act: -0.0001

Data Index: 188221 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6520. Min Act: -0.0001

Data Index: 72209 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6634. Min Act: -0.0001

Data Index: 436304 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6442. Min Act: -0.0001

Data Index: 733136 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6226. Min Act: -0.0001

Data Index: 861031 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6117. Min Act: -0.0001

Data Index: 437772 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6401. Min Act: -0.0001

Data Index: 1306065 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6191. Min Act: -0.0001

Data Index: 1250171 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6101. Min Act: -0.0001

Data Index: 325548 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5930. Min Act: -0.0001

Data Index: 900227 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5771. Min Act: -0.0001

Data Index: 80158 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5884. Min Act: -0.0001

Data Index: 54759 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5883. Min Act: -0.0001

Data Index: 364821 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5790. Min Act: -0.0001

Data Index: 764606 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5948. Min Act: -0.0001

Data Index: 1073797 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5923. Min Act: -0.0001

Data Index: 784970 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5958. Min Act: -0.0001

Data Index: 175157 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5656. Min Act: -0.0001

Data Index: 436160 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5440. Min Act: -0.0001

Data Index: 5426 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5507. Min Act: -0.0001

Data Index: 1183200 (C4 (Web Text))

Max Activating Token Index: 34