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

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

Neuron 3901 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: 0.5894. Min Range: -0.5894

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1375168 (Python Code)

Max Activating Token Index: 132

Text #1

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.5609. Min Act: -0.0000

Data Index: 628617 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1071715 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1195116 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4519. Min Act: -0.0000

Data Index: 1065330 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4441. Min Act: -0.0000

Data Index: 427886 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1410365 (Python Code)

Max Activating Token Index: 654

Text #7

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4329. Min Act: -0.0000

Data Index: 147827 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4023. Min Act: -0.0000

Data Index: 1487192 (Python Code)

Max Activating Token Index: 385

Text #9

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4541. Min Act: -0.0000

Data Index: 960626 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4153. Min Act: -0.0000

Data Index: 606252 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4074. Min Act: -0.0000

Data Index: 350074 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1605397 (Python Code)

Max Activating Token Index: 148

Text #13

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4101. Min Act: -0.0000

Data Index: 807634 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.3693. Min Act: -0.0000

Data Index: 152570 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.3919. Min Act: -0.0000

Data Index: 1589375 (Python Code)

Max Activating Token Index: 862

Text #16

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1577882 (Python Code)

Max Activating Token Index: 445

Text #17

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.3794. Min Act: -0.0000

Data Index: 968528 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.3801. Min Act: -0.0000

Data Index: 1570672 (Python Code)

Max Activating Token Index: 248

Text #19

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.3611. Min Act: -0.0000

Data Index: 298819 (C4 (Web Text))

Max Activating Token Index: 885