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

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

Neuron 3697 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.6199. Min Act: -0.0000

Data Index: 1429165 (Python Code)

Max Activating Token Index: 487

Text #1

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.6086. Min Act: -0.0000

Data Index: 1401570 (Python Code)

Max Activating Token Index: 694

Text #2

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1084173 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5474. Min Act: -0.0000

Data Index: 1171273 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5659. Min Act: -0.0000

Data Index: 1562652 (Python Code)

Max Activating Token Index: 154

Text #5

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1061355 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1444804 (Python Code)

Max Activating Token Index: 671

Text #7

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5054. Min Act: -0.0000

Data Index: 424814 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1550193 (Python Code)

Max Activating Token Index: 895

Text #9

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5151. Min Act: -0.0000

Data Index: 475205 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.4806. Min Act: -0.0000

Data Index: 1622097 (Python Code)

Max Activating Token Index: 390

Text #11

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1426376 (Python Code)

Max Activating Token Index: 315

Text #12

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.4852. Min Act: -0.0000

Data Index: 1568013 (Python Code)

Max Activating Token Index: 693

Text #13

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1494143 (Python Code)

Max Activating Token Index: 929

Text #14

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.4509. Min Act: -0.0000

Data Index: 936738 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1456780 (Python Code)

Max Activating Token Index: 255

Text #16

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.4991. Min Act: -0.0000

Data Index: 121753 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1475311 (Python Code)

Max Activating Token Index: 894

Text #18

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1113910 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.6199. Min Range: -0.6199

Max Act: 0.4943. Min Act: -0.0000

Data Index: 534920 (C4 (Web Text))

Max Activating Token Index: 98