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

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

Neuron 5981 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.8810. Min Act: -0.0000

Data Index: 1402366 (Python Code)

Max Activating Token Index: 968

Text #1

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.8661. Min Act: -0.0000

Data Index: 180745 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.8204. Min Act: -0.0000

Data Index: 1009491 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.7465. Min Act: -0.0001

Data Index: 1071963 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.8057. Min Act: -0.0000

Data Index: 1370270 (Python Code)

Max Activating Token Index: 539

Text #5

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.7767. Min Act: -0.0000

Data Index: 444405 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.7824. Min Act: -0.0000

Data Index: 690251 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.7078. Min Act: -0.0000

Data Index: 1613366 (Python Code)

Max Activating Token Index: 532

Text #8

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1276695 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.6040. Min Act: -0.0000

Data Index: 402425 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.6175. Min Act: -0.0000

Data Index: 466004 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.7338. Min Act: -0.0000

Data Index: 1094560 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.6812. Min Act: -0.0000

Data Index: 782495 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.7122. Min Act: -0.0000

Data Index: 911043 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.6196. Min Act: -0.0001

Data Index: 106493 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.6352. Min Act: -0.0000

Data Index: 975490 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.6919. Min Act: -0.0000

Data Index: 638240 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.6514. Min Act: -0.0000

Data Index: 627473 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.6579. Min Act: -0.0000

Data Index: 1160024 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.6633. Min Act: -0.0000

Data Index: 1286471 (C4 (Web Text))

Max Activating Token Index: 406