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

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

Neuron 2821 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0543. Min Range: -2.0543

Max Act: 2.0543. Min Act: 0.0000

Data Index: 360279 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 2.0543. Min Range: -2.0543

Max Act: 1.9707. Min Act: -0.0000

Data Index: 335045 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 2.0543. Min Range: -2.0543

Max Act: 1.8712. Min Act: -0.0000

Data Index: 1251213 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 2.0543. Min Range: -2.0543

Max Act: 1.7465. Min Act: 0.0000

Data Index: 715666 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 2.0543. Min Range: -2.0543

Max Act: 1.8130. Min Act: -0.0000

Data Index: 564320 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 2.0543. Min Range: -2.0543

Max Act: 1.6523. Min Act: -0.0000

Data Index: 476340 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 2.0543. Min Range: -2.0543

Max Act: 1.5029. Min Act: -0.0000

Data Index: 981820 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 2.0543. Min Range: -2.0543

Max Act: 1.5527. Min Act: -0.0000

Data Index: 22448 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 2.0543. Min Range: -2.0543

Max Act: 1.6037. Min Act: 0.0000

Data Index: 992540 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 2.0543. Min Range: -2.0543

Max Act: 1.5631. Min Act: -0.0000

Data Index: 1130127 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 2.0543. Min Range: -2.0543

Max Act: 1.4822. Min Act: -0.0000

Data Index: 850506 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 2.0543. Min Range: -2.0543

Max Act: 1.4774. Min Act: -0.0000

Data Index: 1497298 (Python Code)

Max Activating Token Index: 873

Text #12

Max Range: 2.0543. Min Range: -2.0543

Max Act: 1.3799. Min Act: -0.0000

Data Index: 92026 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 2.0543. Min Range: -2.0543

Max Act: 1.4606. Min Act: -0.0000

Data Index: 977170 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 2.0543. Min Range: -2.0543

Max Act: 1.4876. Min Act: -0.0000

Data Index: 491546 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 2.0543. Min Range: -2.0543

Max Act: 1.4689. Min Act: -0.0000

Data Index: 796014 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 2.0543. Min Range: -2.0543

Max Act: 1.4387. Min Act: -0.0000

Data Index: 363757 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 2.0543. Min Range: -2.0543

Max Act: 1.3354. Min Act: -0.0000

Data Index: 792042 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 2.0543. Min Range: -2.0543

Max Act: 1.3319. Min Act: -0.0000

Data Index: 1572640 (Python Code)

Max Activating Token Index: 943

Text #19

Max Range: 2.0543. Min Range: -2.0543

Max Act: 1.2014. Min Act: -0.0000

Data Index: 409518 (C4 (Web Text))

Max Activating Token Index: 31