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

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

Neuron 82 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.4104. Min Act: -0.0002

Data Index: 120412 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.3210. Min Act: -0.0002

Data Index: 300459 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.3156. Min Act: -0.0002

Data Index: 940402 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2770. Min Act: -0.0002

Data Index: 223525 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2806. Min Act: -0.0002

Data Index: 388108 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.3004. Min Act: -0.0002

Data Index: 225300 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.3046. Min Act: -0.0002

Data Index: 712421 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2337. Min Act: -0.0002

Data Index: 1432200 (Python Code)

Max Activating Token Index: 867

Text #8

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2071. Min Act: -0.0002

Data Index: 374724 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2095. Min Act: -0.0002

Data Index: 968252 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2034. Min Act: -0.0002

Data Index: 518466 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1797. Min Act: -0.0003

Data Index: 956555 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2048. Min Act: -0.0002

Data Index: 1433125 (Python Code)

Max Activating Token Index: 868

Text #13

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1667. Min Act: -0.0002

Data Index: 956795 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1787. Min Act: -0.0002

Data Index: 903321 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1790. Min Act: -0.0002

Data Index: 274019 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1485. Min Act: -0.0002

Data Index: 315751 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1291. Min Act: -0.0002

Data Index: 640046 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.0977. Min Act: -0.0002

Data Index: 1130386 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1316. Min Act: -0.0002

Data Index: 679444 (C4 (Web Text))

Max Activating Token Index: 161