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

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

Neuron 1762 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9794. Min Range: -4.9794

Max Act: 4.9794. Min Act: -0.0000

Data Index: 284948 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 4.9794. Min Range: -4.9794

Max Act: 4.2295. Min Act: -0.0000

Data Index: 780509 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 4.9794. Min Range: -4.9794

Max Act: 4.1748. Min Act: -0.0000

Data Index: 1331160 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 4.9794. Min Range: -4.9794

Max Act: 3.9942. Min Act: -0.0000

Data Index: 26385 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 4.9794. Min Range: -4.9794

Max Act: 4.1413. Min Act: -0.0000

Data Index: 332253 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 4.9794. Min Range: -4.9794

Max Act: 4.1430. Min Act: -0.0000

Data Index: 983573 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 4.9794. Min Range: -4.9794

Max Act: 4.1007. Min Act: -0.0000

Data Index: 146344 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 4.9794. Min Range: -4.9794

Max Act: 3.9176. Min Act: -0.0000

Data Index: 288808 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 4.9794. Min Range: -4.9794

Max Act: 4.0858. Min Act: -0.0000

Data Index: 533202 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 4.9794. Min Range: -4.9794

Max Act: 4.0420. Min Act: -0.0000

Data Index: 25427 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 4.9794. Min Range: -4.9794

Max Act: 3.9743. Min Act: -0.0000

Data Index: 1108271 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 4.9794. Min Range: -4.9794

Max Act: 3.9923. Min Act: -0.0000

Data Index: 1437028 (Python Code)

Max Activating Token Index: 19

Text #12

Max Range: 4.9794. Min Range: -4.9794

Max Act: 3.9294. Min Act: -0.0000

Data Index: 319928 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 4.9794. Min Range: -4.9794

Max Act: 3.7340. Min Act: -0.0000

Data Index: 733036 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 4.9794. Min Range: -4.9794

Max Act: 3.8945. Min Act: -0.0000

Data Index: 23774 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 4.9794. Min Range: -4.9794

Max Act: 3.8794. Min Act: -0.0000

Data Index: 257233 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 4.9794. Min Range: -4.9794

Max Act: 3.6898. Min Act: -0.0000

Data Index: 182882 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 4.9794. Min Range: -4.9794

Max Act: 3.8510. Min Act: -0.0000

Data Index: 949960 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 4.9794. Min Range: -4.9794

Max Act: 3.8424. Min Act: -0.0000

Data Index: 545101 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 4.9794. Min Range: -4.9794

Max Act: 3.8250. Min Act: -0.0000

Data Index: 392795 (C4 (Web Text))

Max Activating Token Index: 68