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

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

Neuron 2477 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.5546. Min Act: -0.0001

Data Index: 691243 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.5561. Min Act: -0.0001

Data Index: 679691 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.5527. Min Act: -0.0001

Data Index: 192058 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.5486. Min Act: -0.0001

Data Index: 875287 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.5329. Min Act: -0.0001

Data Index: 370780 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.5172. Min Act: -0.0001

Data Index: 429774 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.5064. Min Act: -0.0001

Data Index: 1090166 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.5084. Min Act: -0.0001

Data Index: 44762 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.4862. Min Act: -0.0001

Data Index: 589313 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.4672. Min Act: -0.0001

Data Index: 898158 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.4686. Min Act: -0.0001

Data Index: 1307276 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.4643. Min Act: -0.0001

Data Index: 68202 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.4608. Min Act: -0.0001

Data Index: 377162 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.4874. Min Act: -0.0001

Data Index: 1077816 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.4535. Min Act: -0.0001

Data Index: 879504 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.4676. Min Act: -0.0001

Data Index: 105232 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.4296. Min Act: -0.0001

Data Index: 812415 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.4582. Min Act: -0.0001

Data Index: 929508 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.4062. Min Act: -0.0001

Data Index: 1199902 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.5561. Min Range: -0.5561

Max Act: 0.4381. Min Act: -0.0001

Data Index: 903736 (C4 (Web Text))

Max Activating Token Index: 596