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

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

Neuron 1702 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3932. Min Act: -0.0000

Data Index: 493677 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2652. Min Act: -0.0000

Data Index: 7250 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2740. Min Act: -0.0000

Data Index: 650207 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2418. Min Act: -0.0000

Data Index: 497004 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2492. Min Act: -0.0000

Data Index: 758005 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1514919 (Python Code)

Max Activating Token Index: 65

Text #6

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2210. Min Act: -0.0000

Data Index: 1543827 (Python Code)

Max Activating Token Index: 52

Text #7

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2140. Min Act: -0.0000

Data Index: 414808 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1249115 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2084. Min Act: -0.0000

Data Index: 1579767 (Python Code)

Max Activating Token Index: 839

Text #10

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1327806 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2078. Min Act: -0.0000

Data Index: 1120219 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.1842. Min Act: -0.0000

Data Index: 141826 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.1928. Min Act: -0.0000

Data Index: 256262 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.1926. Min Act: -0.0000

Data Index: 1435793 (Python Code)

Max Activating Token Index: 103

Text #15

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.1900. Min Act: -0.0000

Data Index: 131340 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.1865. Min Act: -0.0000

Data Index: 48246 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.1779. Min Act: -0.0000

Data Index: 180604 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1293061 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.1858. Min Act: -0.0000

Data Index: 1034683 (C4 (Web Text))

Max Activating Token Index: 655