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

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

Neuron 2813 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: 0.2105. Min Range: -0.2105

Max Act: 0.2105. Min Act: -0.0001

Data Index: 670671 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1953. Min Act: -0.0001

Data Index: 958199 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1994. Min Act: -0.0001

Data Index: 907277 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.2042. Min Act: -0.0001

Data Index: 34835 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1806. Min Act: -0.0001

Data Index: 753708 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1909. Min Act: -0.0001

Data Index: 131583 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1818. Min Act: -0.0001

Data Index: 5087 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.2022. Min Act: -0.0001

Data Index: 206200 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1803. Min Act: -0.0001

Data Index: 102660 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1766. Min Act: -0.0001

Data Index: 793671 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1702. Min Act: -0.0001

Data Index: 571277 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1845. Min Act: -0.0001

Data Index: 42825 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1841. Min Act: -0.0001

Data Index: 495610 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1737. Min Act: -0.0001

Data Index: 773431 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1671. Min Act: -0.0001

Data Index: 93209 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1531. Min Act: -0.0001

Data Index: 669190 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1793. Min Act: -0.0001

Data Index: 49029 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1565. Min Act: -0.0001

Data Index: 1247661 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1719. Min Act: -0.0001

Data Index: 412582 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1910. Min Act: -0.0001

Data Index: 579043 (C4 (Web Text))

Max Activating Token Index: 732