Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1556 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7138. Min Act: -0.0001

Data Index: 1448705 (Python Code)

Max Activating Token Index: 185

Text #1

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7597. Min Act: -0.0001

Data Index: 1582855 (Python Code)

Max Activating Token Index: 258

Text #2

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7195. Min Act: -0.0001

Data Index: 1634450 (Python Code)

Max Activating Token Index: 145

Text #3

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7236. Min Act: -0.0001

Data Index: 1577023 (Python Code)

Max Activating Token Index: 104

Text #4

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7226. Min Act: -0.0001

Data Index: 1592739 (Python Code)

Max Activating Token Index: 133

Text #5

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7155. Min Act: -0.0001

Data Index: 1490627 (Python Code)

Max Activating Token Index: 95

Text #6

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7013. Min Act: -0.0001

Data Index: 1397401 (Python Code)

Max Activating Token Index: 144

Text #7

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6968. Min Act: -0.0001

Data Index: 1648441 (Python Code)

Max Activating Token Index: 169

Text #8

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6945. Min Act: -0.0001

Data Index: 1365977 (Python Code)

Max Activating Token Index: 214

Text #9

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6897. Min Act: -0.0001

Data Index: 1468909 (Python Code)

Max Activating Token Index: 678

Text #10

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7186. Min Act: -0.0001

Data Index: 1459312 (Python Code)

Max Activating Token Index: 213

Text #11

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6950. Min Act: -0.0001

Data Index: 1497194 (Python Code)

Max Activating Token Index: 128

Text #12

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7114. Min Act: -0.0001

Data Index: 1458824 (Python Code)

Max Activating Token Index: 302

Text #13

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7355. Min Act: -0.0001

Data Index: 1574125 (Python Code)

Max Activating Token Index: 146

Text #14

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7101. Min Act: -0.0001

Data Index: 1411775 (Python Code)

Max Activating Token Index: 232

Text #15

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6929. Min Act: -0.0001

Data Index: 1430856 (Python Code)

Max Activating Token Index: 287

Text #16

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7069. Min Act: -0.0001

Data Index: 1429911 (Python Code)

Max Activating Token Index: 275

Text #17

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7199. Min Act: -0.0001

Data Index: 1655328 (Python Code)

Max Activating Token Index: 152

Text #18

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6558. Min Act: -0.0001

Data Index: 1364721 (Python Code)

Max Activating Token Index: 614

Text #19

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6784. Min Act: -0.0001

Data Index: 1390778 (Python Code)

Max Activating Token Index: 419