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

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

Neuron 1097 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: 0.0756. Min Range: -0.0756

Max Act: 0.0728. Min Act: -0.0002

Data Index: 415546 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0716. Min Act: -0.0001

Data Index: 591767 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1255492 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0539. Min Act: -0.0002

Data Index: 127826 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0746. Min Act: -0.0002

Data Index: 171561 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0410. Min Act: -0.0001

Data Index: 360798 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0536. Min Act: -0.0001

Data Index: 906418 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0607. Min Act: -0.0001

Data Index: 482027 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1268071 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0461. Min Act: -0.0001

Data Index: 426197 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1001134 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0579. Min Act: -0.0002

Data Index: 682328 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1346873 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0548. Min Act: -0.0002

Data Index: 19376 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0629. Min Act: -0.0002

Data Index: 204579 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0537. Min Act: -0.0002

Data Index: 274369 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0478. Min Act: -0.0002

Data Index: 504871 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0475. Min Act: -0.0002

Data Index: 325528 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0566. Min Act: -0.0002

Data Index: 612843 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0509. Min Act: -0.0002

Data Index: 894120 (C4 (Web Text))

Max Activating Token Index: 26