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

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

Neuron 2281 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3011. Min Range: -2.3011

Max Act: 2.2346. Min Act: -0.0000

Data Index: 815037 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 2.3011. Min Range: -2.3011

Max Act: 2.3011. Min Act: -0.0000

Data Index: 1198536 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 2.3011. Min Range: -2.3011

Max Act: 2.1938. Min Act: -0.0000

Data Index: 960783 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 2.3011. Min Range: -2.3011

Max Act: 2.0496. Min Act: -0.0000

Data Index: 823701 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 2.3011. Min Range: -2.3011

Max Act: 2.0515. Min Act: -0.0000

Data Index: 392731 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 2.3011. Min Range: -2.3011

Max Act: 1.9068. Min Act: -0.0000

Data Index: 245332 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 2.3011. Min Range: -2.3011

Max Act: 1.9887. Min Act: -0.0000

Data Index: 862113 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 2.3011. Min Range: -2.3011

Max Act: 1.8680. Min Act: -0.0000

Data Index: 418924 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 2.3011. Min Range: -2.3011

Max Act: 1.8961. Min Act: -0.0000

Data Index: 624410 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 2.3011. Min Range: -2.3011

Max Act: 1.7622. Min Act: -0.0000

Data Index: 13571 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 2.3011. Min Range: -2.3011

Max Act: 1.8826. Min Act: -0.0000

Data Index: 1455959 (Python Code)

Max Activating Token Index: 844

Text #11

Max Range: 2.3011. Min Range: -2.3011

Max Act: 1.7882. Min Act: -0.0000

Data Index: 955718 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 2.3011. Min Range: -2.3011

Max Act: 1.7776. Min Act: -0.0000

Data Index: 666601 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 2.3011. Min Range: -2.3011

Max Act: 1.8781. Min Act: -0.0000

Data Index: 1564248 (Python Code)

Max Activating Token Index: 711

Text #14

Max Range: 2.3011. Min Range: -2.3011

Max Act: 1.8765. Min Act: -0.0000

Data Index: 611015 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 2.3011. Min Range: -2.3011

Max Act: 1.7103. Min Act: -0.0000

Data Index: 983720 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 2.3011. Min Range: -2.3011

Max Act: 1.7002. Min Act: -0.0000

Data Index: 752282 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 2.3011. Min Range: -2.3011

Max Act: 1.6092. Min Act: -0.0000

Data Index: 388123 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 2.3011. Min Range: -2.3011

Max Act: 1.6872. Min Act: -0.0000

Data Index: 555728 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 2.3011. Min Range: -2.3011

Max Act: 1.6590. Min Act: -0.0000

Data Index: 198953 (C4 (Web Text))

Max Activating Token Index: 437