Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1905 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.2167. Min Act: -0.0001

Data Index: 473138 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1606. Min Act: -0.0001

Data Index: 436880 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1094. Min Act: -0.0001

Data Index: 875580 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.0932. Min Act: -0.0000

Data Index: 1623609 (Python Code)

Max Activating Token Index: 763

Text #4

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.0784. Min Act: -0.0000

Data Index: 1276639 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.0810. Min Act: -0.0000

Data Index: 1500739 (Python Code)

Max Activating Token Index: 757

Text #6

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.0776. Min Act: -0.0001

Data Index: 4745 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.0801. Min Act: -0.0001

Data Index: 576340 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.0784. Min Act: -0.0000

Data Index: 620211 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1488530 (Python Code)

Max Activating Token Index: 510

Text #10

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.0736. Min Act: -0.0001

Data Index: 923415 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.0759. Min Act: -0.0001

Data Index: 59994 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.0759. Min Act: -0.0000

Data Index: 1081161 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.0778. Min Act: -0.0001

Data Index: 843343 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.0776. Min Act: -0.0000

Data Index: 906995 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.0739. Min Act: -0.0000

Data Index: 1243508 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.0733. Min Act: -0.0001

Data Index: 282596 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1168060 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.0719. Min Act: -0.0001

Data Index: 383790 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1035370 (C4 (Web Text))

Max Activating Token Index: 700