Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4858 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.7771. Min Range: -4.7771

Max Act: 4.7771. Min Act: -0.0000

Data Index: 1278137 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 4.7771. Min Range: -4.7771

Max Act: 4.3755. Min Act: -0.0000

Data Index: 523372 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 4.7771. Min Range: -4.7771

Max Act: 4.0811. Min Act: -0.0000

Data Index: 1046450 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 4.7771. Min Range: -4.7771

Max Act: 4.1477. Min Act: -0.0000

Data Index: 516352 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 4.7771. Min Range: -4.7771

Max Act: 4.1577. Min Act: -0.0000

Data Index: 1344831 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 4.7771. Min Range: -4.7771

Max Act: 3.9543. Min Act: -0.0000

Data Index: 690958 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 4.7771. Min Range: -4.7771

Max Act: 3.9412. Min Act: -0.0000

Data Index: 68487 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 4.7771. Min Range: -4.7771

Max Act: 3.9141. Min Act: -0.0000

Data Index: 594119 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 4.7771. Min Range: -4.7771

Max Act: 3.9352. Min Act: -0.0000

Data Index: 1340376 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 4.7771. Min Range: -4.7771

Max Act: 4.0543. Min Act: -0.0000

Data Index: 682742 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 4.7771. Min Range: -4.7771

Max Act: 3.8492. Min Act: -0.0000

Data Index: 18742 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 4.7771. Min Range: -4.7771

Max Act: 3.8148. Min Act: -0.0000

Data Index: 159164 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 4.7771. Min Range: -4.7771

Max Act: 3.9260. Min Act: -0.0000

Data Index: 52741 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 4.7771. Min Range: -4.7771

Max Act: 3.8053. Min Act: -0.0000

Data Index: 722412 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 4.7771. Min Range: -4.7771

Max Act: 3.7331. Min Act: -0.0000

Data Index: 516172 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 4.7771. Min Range: -4.7771

Max Act: 3.9105. Min Act: -0.0000

Data Index: 1003922 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 4.7771. Min Range: -4.7771

Max Act: 3.7115. Min Act: -0.0000

Data Index: 1000165 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 4.7771. Min Range: -4.7771

Max Act: 3.9968. Min Act: -0.0000

Data Index: 748235 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 4.7771. Min Range: -4.7771

Max Act: 3.8619. Min Act: -0.0000

Data Index: 218014 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 4.7771. Min Range: -4.7771

Max Act: 3.6206. Min Act: -0.0000

Data Index: 398597 (C4 (Web Text))

Max Activating Token Index: 160