Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3530 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4135. Min Range: -3.4135

Max Act: 3.4135. Min Act: -0.0001

Data Index: 533013 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 3.4135. Min Range: -3.4135

Max Act: 3.2118. Min Act: -0.0001

Data Index: 377487 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 3.4135. Min Range: -3.4135

Max Act: 3.2889. Min Act: -0.0001

Data Index: 184106 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 3.4135. Min Range: -3.4135

Max Act: 3.2291. Min Act: -0.0000

Data Index: 1333580 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 3.4135. Min Range: -3.4135

Max Act: 3.3951. Min Act: -0.0001

Data Index: 1163920 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 3.4135. Min Range: -3.4135

Max Act: 2.9791. Min Act: -0.0001

Data Index: 369781 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 3.4135. Min Range: -3.4135

Max Act: 3.0467. Min Act: -0.0000

Data Index: 1280179 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 3.4135. Min Range: -3.4135

Max Act: 2.9339. Min Act: -0.0001

Data Index: 1022122 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 3.4135. Min Range: -3.4135

Max Act: 2.7450. Min Act: -0.0000

Data Index: 1161264 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 3.4135. Min Range: -3.4135

Max Act: 2.7172. Min Act: -0.0001

Data Index: 190202 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 3.4135. Min Range: -3.4135

Max Act: 2.8541. Min Act: -0.0001

Data Index: 585618 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 3.4135. Min Range: -3.4135

Max Act: 3.0022. Min Act: -0.0001

Data Index: 569808 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 3.4135. Min Range: -3.4135

Max Act: 2.7227. Min Act: -0.0001

Data Index: 65194 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 3.4135. Min Range: -3.4135

Max Act: 2.6038. Min Act: -0.0000

Data Index: 1189765 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 3.4135. Min Range: -3.4135

Max Act: 2.7163. Min Act: -0.0001

Data Index: 506507 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 3.4135. Min Range: -3.4135

Max Act: 2.7052. Min Act: -0.0001

Data Index: 1235260 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 3.4135. Min Range: -3.4135

Max Act: 2.6681. Min Act: -0.0001

Data Index: 498072 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 3.4135. Min Range: -3.4135

Max Act: 2.4456. Min Act: -0.0001

Data Index: 1018811 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 3.4135. Min Range: -3.4135

Max Act: 2.5582. Min Act: -0.0001

Data Index: 677659 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 3.4135. Min Range: -3.4135

Max Act: 2.6688. Min Act: -0.0001

Data Index: 1104697 (C4 (Web Text))

Max Activating Token Index: 578