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

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

Neuron 2014 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1182008 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.6368. Min Act: -0.0000

Data Index: 294237 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1152437 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.5421. Min Act: -0.0000

Data Index: 678714 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.5132. Min Act: -0.0000

Data Index: 70353 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.5132. Min Act: -0.0000

Data Index: 779517 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1216378 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.5431. Min Act: -0.0000

Data Index: 212942 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1131535 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.4828. Min Act: -0.0000

Data Index: 881046 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.4938. Min Act: -0.0000

Data Index: 552275 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.4381. Min Act: -0.0000

Data Index: 525213 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.4489. Min Act: -0.0000

Data Index: 760278 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.4651. Min Act: -0.0000

Data Index: 673745 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.4404. Min Act: -0.0000

Data Index: 516122 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.4552. Min Act: -0.0000

Data Index: 470774 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1615408 (Python Code)

Max Activating Token Index: 239

Text #17

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.4146. Min Act: -0.0000

Data Index: 16674 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1050434 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.4477. Min Act: -0.0000

Data Index: 960112 (C4 (Web Text))

Max Activating Token Index: 319