Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1938 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1337594 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.5167. Min Act: -0.0000

Data Index: 678310 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.5641. Min Act: -0.0000

Data Index: 1280777 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.5026. Min Act: -0.0000

Data Index: 877403 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.4966. Min Act: -0.0000

Data Index: 29585 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1042072 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.4318. Min Act: -0.0000

Data Index: 449400 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.4289. Min Act: -0.0000

Data Index: 547352 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.4017. Min Act: -0.0000

Data Index: 3090 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.4009. Min Act: -0.0000

Data Index: 58528 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1305023 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.3917. Min Act: -0.0000

Data Index: 761432 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1274880 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.3840. Min Act: -0.0000

Data Index: 558889 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.3765. Min Act: -0.0000

Data Index: 495021 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.3909. Min Act: -0.0000

Data Index: 216330 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.3883. Min Act: -0.0000

Data Index: 364881 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1109274 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.3704. Min Act: -0.0000

Data Index: 443688 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1220464 (C4 (Web Text))

Max Activating Token Index: 596