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

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

Neuron 4967 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: 1.6978. Min Range: -1.6978

Max Act: 1.6978. Min Act: -0.0002

Data Index: 501649 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.5425. Min Act: -0.0002

Data Index: 883304 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.4823. Min Act: -0.0002

Data Index: 524741 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.4413. Min Act: -0.0002

Data Index: 275448 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.4213. Min Act: -0.0002

Data Index: 96113 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.4242. Min Act: -0.0002

Data Index: 1243995 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.3917. Min Act: -0.0002

Data Index: 1343077 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.3931. Min Act: -0.0002

Data Index: 678114 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.3896. Min Act: -0.0002

Data Index: 719863 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.3578. Min Act: -0.0002

Data Index: 409957 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.3778. Min Act: -0.0002

Data Index: 675609 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.3676. Min Act: -0.0002

Data Index: 53534 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.3513. Min Act: -0.0002

Data Index: 187762 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.3559. Min Act: -0.0002

Data Index: 712483 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.3632. Min Act: -0.0002

Data Index: 1163636 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.3527. Min Act: -0.0002

Data Index: 538455 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.3387. Min Act: -0.0002

Data Index: 333849 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.3063. Min Act: -0.0002

Data Index: 480708 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.3243. Min Act: -0.0002

Data Index: 588187 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.3111. Min Act: -0.0002

Data Index: 733042 (C4 (Web Text))

Max Activating Token Index: 425