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

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

Neuron 3908 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.9438. Min Act: -0.0002

Data Index: 872199 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.9358. Min Act: -0.0002

Data Index: 1307240 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8826. Min Act: -0.0002

Data Index: 1342803 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8433. Min Act: -0.0002

Data Index: 1338328 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8636. Min Act: -0.0002

Data Index: 214214 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8639. Min Act: -0.0002

Data Index: 749604 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8774. Min Act: -0.0002

Data Index: 74511 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8438. Min Act: -0.0002

Data Index: 81797 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8187. Min Act: -0.0002

Data Index: 1129212 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8291. Min Act: -0.0002

Data Index: 624956 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8246. Min Act: -0.0001

Data Index: 918744 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7757. Min Act: -0.0002

Data Index: 560096 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8217. Min Act: -0.0002

Data Index: 530847 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8230. Min Act: -0.0002

Data Index: 552507 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8099. Min Act: -0.0001

Data Index: 1009376 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8349. Min Act: -0.0002

Data Index: 685917 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7896. Min Act: -0.0001

Data Index: 687050 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7967. Min Act: -0.0002

Data Index: 296231 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8111. Min Act: -0.0002

Data Index: 471205 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7890. Min Act: -0.0002

Data Index: 98001 (C4 (Web Text))

Max Activating Token Index: 79