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

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

Neuron 1346 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.5254. Min Act: -0.0001

Data Index: 361855 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.5504. Min Act: -0.0001

Data Index: 950023 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4935. Min Act: -0.0001

Data Index: 1247349 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4790. Min Act: -0.0001

Data Index: 392129 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4684. Min Act: -0.0001

Data Index: 827425 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4733. Min Act: -0.0001

Data Index: 401923 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4988. Min Act: -0.0001

Data Index: 1063461 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4584. Min Act: -0.0001

Data Index: 45192 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4489. Min Act: -0.0001

Data Index: 422084 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4378. Min Act: -0.0001

Data Index: 446305 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4556. Min Act: -0.0001

Data Index: 1245909 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4388. Min Act: -0.0001

Data Index: 361173 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4650. Min Act: -0.0001

Data Index: 355843 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4468. Min Act: -0.0001

Data Index: 528721 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4473. Min Act: -0.0001

Data Index: 1332480 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4136. Min Act: -0.0001

Data Index: 1230499 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.3748. Min Act: -0.0001

Data Index: 1339387 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4138. Min Act: -0.0001

Data Index: 337952 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4661. Min Act: -0.0001

Data Index: 470903 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.5504. Min Range: -0.5504

Max Act: 0.4220. Min Act: -0.0001

Data Index: 866733 (C4 (Web Text))

Max Activating Token Index: 465