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

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

Neuron 780 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: 0.1311. Min Range: -0.1311

Max Act: 0.1311. Min Act: -0.0000

Data Index: 1408434 (Python Code)

Max Activating Token Index: 187

Text #1

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1260. Min Act: -0.0000

Data Index: 264109 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1263. Min Act: -0.0000

Data Index: 510988 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1258. Min Act: -0.0000

Data Index: 272663 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1154. Min Act: -0.0001

Data Index: 20619 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1105. Min Act: -0.0000

Data Index: 1314234 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1126. Min Act: -0.0000

Data Index: 1453790 (Python Code)

Max Activating Token Index: 158

Text #7

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1327367 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1045844 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1043. Min Act: -0.0000

Data Index: 979396 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0966. Min Act: -0.0000

Data Index: 558950 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1586099 (Python Code)

Max Activating Token Index: 238

Text #12

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0957. Min Act: -0.0000

Data Index: 570350 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0949. Min Act: -0.0000

Data Index: 172178 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1206333 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1448663 (Python Code)

Max Activating Token Index: 649

Text #16

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1135591 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1437918 (Python Code)

Max Activating Token Index: 587

Text #18

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0879. Min Act: -0.0000

Data Index: 750829 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0906. Min Act: -0.0000

Data Index: 659664 (C4 (Web Text))

Max Activating Token Index: 247