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

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

Neuron 214 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: 0.2891. Min Range: -0.2891

Max Act: 0.2891. Min Act: -0.0001

Data Index: 894644 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2174. Min Act: -0.0001

Data Index: 290358 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2021. Min Act: -0.0001

Data Index: 538932 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1885. Min Act: -0.0001

Data Index: 1502691 (Python Code)

Max Activating Token Index: 171

Text #4

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1989. Min Act: -0.0001

Data Index: 506256 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1036061 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2011. Min Act: -0.0001

Data Index: 1048022 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1776. Min Act: -0.0001

Data Index: 160832 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2015. Min Act: -0.0000

Data Index: 266478 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1804. Min Act: -0.0001

Data Index: 329089 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1888. Min Act: -0.0001

Data Index: 1089667 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1745. Min Act: -0.0000

Data Index: 441689 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1818. Min Act: -0.0000

Data Index: 924921 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1786. Min Act: -0.0001

Data Index: 250584 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1768. Min Act: -0.0000

Data Index: 1319092 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1671. Min Act: -0.0001

Data Index: 348113 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1594. Min Act: -0.0001

Data Index: 419649 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1228703 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1645. Min Act: -0.0000

Data Index: 891250 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1677. Min Act: -0.0001

Data Index: 184367 (C4 (Web Text))

Max Activating Token Index: 545