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

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

Neuron 3455 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1793. Min Range: -3.1793

Max Act: 3.1793. Min Act: -0.0001

Data Index: 1085979 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 3.1793. Min Range: -3.1793

Max Act: 2.9068. Min Act: -0.0001

Data Index: 1081852 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 3.1793. Min Range: -3.1793

Max Act: 2.7847. Min Act: -0.0000

Data Index: 433292 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 3.1793. Min Range: -3.1793

Max Act: 2.4681. Min Act: -0.0001

Data Index: 1158406 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 3.1793. Min Range: -3.1793

Max Act: 2.4604. Min Act: -0.0000

Data Index: 991066 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 3.1793. Min Range: -3.1793

Max Act: 2.5196. Min Act: -0.0001

Data Index: 813459 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 3.1793. Min Range: -3.1793

Max Act: 2.3589. Min Act: -0.0001

Data Index: 1170532 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.1793. Min Range: -3.1793

Max Act: 2.2728. Min Act: -0.0001

Data Index: 684923 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 3.1793. Min Range: -3.1793

Max Act: 2.2502. Min Act: -0.0001

Data Index: 707667 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 3.1793. Min Range: -3.1793

Max Act: 2.1242. Min Act: -0.0001

Data Index: 649026 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 3.1793. Min Range: -3.1793

Max Act: 1.9775. Min Act: -0.0001

Data Index: 1205960 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 3.1793. Min Range: -3.1793

Max Act: 2.3106. Min Act: -0.0001

Data Index: 1259303 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 3.1793. Min Range: -3.1793

Max Act: 2.1669. Min Act: -0.0001

Data Index: 37246 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 3.1793. Min Range: -3.1793

Max Act: 2.1783. Min Act: -0.0001

Data Index: 1311898 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 3.1793. Min Range: -3.1793

Max Act: 2.0534. Min Act: -0.0001

Data Index: 571736 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 3.1793. Min Range: -3.1793

Max Act: 2.1256. Min Act: -0.0001

Data Index: 1126622 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 3.1793. Min Range: -3.1793

Max Act: 2.1319. Min Act: -0.0001

Data Index: 1039707 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 3.1793. Min Range: -3.1793

Max Act: 2.0269. Min Act: -0.0001

Data Index: 1174274 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 3.1793. Min Range: -3.1793

Max Act: 1.9922. Min Act: -0.0001

Data Index: 862355 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 3.1793. Min Range: -3.1793

Max Act: 2.1154. Min Act: -0.0001

Data Index: 377643 (C4 (Web Text))

Max Activating Token Index: 543