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

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

Neuron 22 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.9740. Min Act: -0.0000

Data Index: 735967 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.6844. Min Act: -0.0000

Data Index: 723079 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.5562. Min Act: -0.0000

Data Index: 1626588 (Python Code)

Max Activating Token Index: 313

Text #3

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.2942. Min Act: -0.0000

Data Index: 458419 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.5284. Min Act: -0.0000

Data Index: 487773 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.6307. Min Act: -0.0000

Data Index: 217590 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.3726. Min Act: -0.0000

Data Index: 427037 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.4280. Min Act: -0.0000

Data Index: 776191 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.2945. Min Act: -0.0000

Data Index: 540013 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.2820. Min Act: -0.0000

Data Index: 482016 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.2521. Min Act: -0.0000

Data Index: 472785 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.2102. Min Act: -0.0000

Data Index: 368407 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.1498. Min Act: -0.0000

Data Index: 16221 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.2518. Min Act: -0.0000

Data Index: 1317768 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.2505. Min Act: -0.0000

Data Index: 328429 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.3156. Min Act: -0.0000

Data Index: 612325 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.3672. Min Act: -0.0000

Data Index: 473905 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.2704. Min Act: -0.0000

Data Index: 246350 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.1838. Min Act: -0.0000

Data Index: 863942 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 1.9740. Min Range: -1.9740

Max Act: 1.2285. Min Act: -0.0000

Data Index: 668452 (C4 (Web Text))

Max Activating Token Index: 531