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

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

Neuron 1676 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.9612. Min Act: -0.0001

Data Index: 88042 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.4431. Min Act: -0.0001

Data Index: 106306 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.5108. Min Act: -0.0001

Data Index: 1291652 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.5345. Min Act: -0.0001

Data Index: 973233 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.5753. Min Act: -0.0001

Data Index: 633584 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.3204. Min Act: -0.0001

Data Index: 882128 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.4299. Min Act: -0.0001

Data Index: 1359007 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.3371. Min Act: -0.0001

Data Index: 901995 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.3063. Min Act: -0.0001

Data Index: 457418 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.3751. Min Act: -0.0001

Data Index: 1156511 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.3624. Min Act: -0.0001

Data Index: 797642 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.3630. Min Act: -0.0001

Data Index: 1064359 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.2445. Min Act: -0.0001

Data Index: 319607 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.3606. Min Act: -0.0001

Data Index: 624980 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.4412. Min Act: -0.0001

Data Index: 1059502 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.3828. Min Act: -0.0001

Data Index: 566005 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.2617. Min Act: -0.0001

Data Index: 109311 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.3320. Min Act: -0.0001

Data Index: 1116517 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.4187. Min Act: -0.0001

Data Index: 360109 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 1.9612. Min Range: -1.9612

Max Act: 1.2870. Min Act: -0.0001

Data Index: 696574 (C4 (Web Text))

Max Activating Token Index: 1003