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

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

Neuron 3683 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1883. Min Act: -0.0000

Data Index: 52012 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1763. Min Act: -0.0000

Data Index: 760752 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1609. Min Act: -0.0000

Data Index: 261749 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1536. Min Act: -0.0000

Data Index: 746615 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1410. Min Act: -0.0000

Data Index: 500295 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1538. Min Act: -0.0000

Data Index: 1065848 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1281. Min Act: -0.0000

Data Index: 1161216 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1356. Min Act: -0.0000

Data Index: 756784 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1377. Min Act: -0.0000

Data Index: 880110 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1326. Min Act: -0.0000

Data Index: 139320 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1317. Min Act: -0.0000

Data Index: 815283 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1343. Min Act: -0.0000

Data Index: 187159 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1361. Min Act: -0.0000

Data Index: 962210 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1000002 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1009246 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1269. Min Act: -0.0000

Data Index: 242147 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1262. Min Act: -0.0000

Data Index: 208895 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1191. Min Act: -0.0000

Data Index: 98794 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1101. Min Act: -0.0000

Data Index: 553857 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1165. Min Act: -0.0000

Data Index: 715176 (C4 (Web Text))

Max Activating Token Index: 916