Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1612 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.2002. Min Act: -0.0000

Data Index: 1292775 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1729. Min Act: -0.0000

Data Index: 212555 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.0229. Min Act: -0.0000

Data Index: 1313614 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.9419. Min Act: -0.0000

Data Index: 1259219 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.9551. Min Act: -0.0000

Data Index: 1325335 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.8154. Min Act: -0.0000

Data Index: 990571 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.7881. Min Act: -0.0000

Data Index: 1281259 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.8291. Min Act: -0.0000

Data Index: 1314139 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.7596. Min Act: -0.0000

Data Index: 124360 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.7640. Min Act: -0.0000

Data Index: 55579 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.7830. Min Act: -0.0000

Data Index: 155822 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.7334. Min Act: -0.0000

Data Index: 561869 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.7160. Min Act: -0.0000

Data Index: 594148 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.7513. Min Act: -0.0000

Data Index: 794221 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.7038. Min Act: -0.0000

Data Index: 93549 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.7504. Min Act: -0.0000

Data Index: 944473 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.6855. Min Act: -0.0000

Data Index: 357259 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.7190. Min Act: -0.0000

Data Index: 411843 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.7036. Min Act: -0.0000

Data Index: 1274339 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.7005. Min Act: -0.0000

Data Index: 1196035 (C4 (Web Text))

Max Activating Token Index: 378