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

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

Neuron 2472 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: 1.9438. Min Range: -1.9438

Max Act: 1.9438. Min Act: -0.0001

Data Index: 156832 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.6428. Min Act: -0.0001

Data Index: 625942 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.6929. Min Act: -0.0001

Data Index: 806955 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.7048. Min Act: -0.0001

Data Index: 190776 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.8017. Min Act: -0.0001

Data Index: 1170391 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.4394. Min Act: -0.0001

Data Index: 38717 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.4658. Min Act: -0.0001

Data Index: 1653852 (Python Code)

Max Activating Token Index: 769

Text #7

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.4507. Min Act: -0.0001

Data Index: 1046659 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.4530. Min Act: -0.0001

Data Index: 307613 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.3736. Min Act: -0.0000

Data Index: 1233781 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.3910. Min Act: -0.0001

Data Index: 209820 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.3356. Min Act: -0.0001

Data Index: 710472 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.3598. Min Act: -0.0001

Data Index: 1010794 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.3502. Min Act: -0.0001

Data Index: 1354924 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.2944. Min Act: -0.0001

Data Index: 1031565 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.3236. Min Act: -0.0001

Data Index: 1105959 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.3699. Min Act: -0.0001

Data Index: 1075387 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.3602. Min Act: -0.0001

Data Index: 72603 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.3117. Min Act: -0.0001

Data Index: 613165 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.2337. Min Act: -0.0001

Data Index: 517920 (C4 (Web Text))

Max Activating Token Index: 806