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

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

Neuron 2440 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5667. Min Act: 0.0001

Data Index: 509393 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5592. Min Act: -0.0000

Data Index: 746437 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5546. Min Act: -0.0000

Data Index: 1299148 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5060. Min Act: -0.0001

Data Index: 100475 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5003. Min Act: -0.0000

Data Index: 853429 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4939. Min Act: -0.0001

Data Index: 821665 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4691. Min Act: -0.0000

Data Index: 1292526 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4682. Min Act: -0.0001

Data Index: 1091604 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4912. Min Act: -0.0000

Data Index: 353956 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4700. Min Act: -0.0001

Data Index: 495535 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4681. Min Act: -0.0000

Data Index: 1000 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4718. Min Act: -0.0001

Data Index: 782825 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4795. Min Act: -0.0001

Data Index: 999951 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1176841 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4435. Min Act: -0.0000

Data Index: 880679 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4451. Min Act: 0.0002

Data Index: 1288348 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4518. Min Act: -0.0001

Data Index: 363064 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4535. Min Act: -0.0000

Data Index: 1346239 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4799. Min Act: -0.0000

Data Index: 310659 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4562. Min Act: -0.0000

Data Index: 863398 (C4 (Web Text))

Max Activating Token Index: 865