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

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

Neuron 1948 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3910. Min Range: -2.3910

Max Act: 2.3910. Min Act: -0.0001

Data Index: 195061 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 2.3910. Min Range: -2.3910

Max Act: 2.2659. Min Act: -0.0000

Data Index: 471186 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 2.3910. Min Range: -2.3910

Max Act: 2.1766. Min Act: -0.0001

Data Index: 971413 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 2.3910. Min Range: -2.3910

Max Act: 2.0224. Min Act: -0.0001

Data Index: 638882 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 2.3910. Min Range: -2.3910

Max Act: 1.9802. Min Act: -0.0001

Data Index: 719098 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 2.3910. Min Range: -2.3910

Max Act: 2.0724. Min Act: -0.0001

Data Index: 275816 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 2.3910. Min Range: -2.3910

Max Act: 1.8629. Min Act: -0.0000

Data Index: 92255 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 2.3910. Min Range: -2.3910

Max Act: 1.9144. Min Act: -0.0000

Data Index: 1313567 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 2.3910. Min Range: -2.3910

Max Act: 1.7722. Min Act: -0.0000

Data Index: 905289 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 2.3910. Min Range: -2.3910

Max Act: 1.7225. Min Act: -0.0000

Data Index: 384089 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 2.3910. Min Range: -2.3910

Max Act: 1.7142. Min Act: -0.0001

Data Index: 601681 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 2.3910. Min Range: -2.3910

Max Act: 1.7260. Min Act: -0.0000

Data Index: 1140582 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 2.3910. Min Range: -2.3910

Max Act: 1.6587. Min Act: -0.0001

Data Index: 384408 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 2.3910. Min Range: -2.3910

Max Act: 1.5941. Min Act: -0.0000

Data Index: 623685 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 2.3910. Min Range: -2.3910

Max Act: 1.6665. Min Act: -0.0000

Data Index: 709464 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 2.3910. Min Range: -2.3910

Max Act: 1.5714. Min Act: -0.0001

Data Index: 1263833 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 2.3910. Min Range: -2.3910

Max Act: 1.6277. Min Act: -0.0001

Data Index: 896441 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 2.3910. Min Range: -2.3910

Max Act: 1.6221. Min Act: -0.0001

Data Index: 439503 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 2.3910. Min Range: -2.3910

Max Act: 1.6054. Min Act: -0.0001

Data Index: 198666 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 2.3910. Min Range: -2.3910

Max Act: 1.6335. Min Act: -0.0001

Data Index: 301057 (C4 (Web Text))

Max Activating Token Index: 955