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

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

Neuron 513 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4598. Min Act: -0.0001

Data Index: 274212 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4733. Min Act: -0.0001

Data Index: 783235 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4682. Min Act: -0.0001

Data Index: 134311 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4104. Min Act: -0.0001

Data Index: 452545 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4090. Min Act: -0.0001

Data Index: 1175166 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4109. Min Act: -0.0001

Data Index: 16084 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3701. Min Act: -0.0001

Data Index: 880000 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3803. Min Act: -0.0001

Data Index: 50991 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3668. Min Act: -0.0001

Data Index: 852984 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3876. Min Act: -0.0001

Data Index: 569024 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3735. Min Act: -0.0001

Data Index: 1351721 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3742. Min Act: -0.0001

Data Index: 856179 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3705. Min Act: -0.0001

Data Index: 643130 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3666. Min Act: -0.0001

Data Index: 423596 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3802. Min Act: -0.0001

Data Index: 85867 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3628. Min Act: -0.0001

Data Index: 1062551 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3634. Min Act: -0.0001

Data Index: 1344388 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3640. Min Act: -0.0001

Data Index: 31069 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3633. Min Act: -0.0001

Data Index: 144889 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3616. Min Act: -0.0001

Data Index: 1334075 (C4 (Web Text))

Max Activating Token Index: 167