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

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

Neuron 3415 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: 1.9457. Min Range: -1.9457

Max Act: 1.9457. Min Act: -0.0000

Data Index: 317157 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 1.9457. Min Range: -1.9457

Max Act: 1.6403. Min Act: -0.0000

Data Index: 968494 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 1.9457. Min Range: -1.9457

Max Act: 1.4507. Min Act: -0.0000

Data Index: 1623293 (Python Code)

Max Activating Token Index: 172

Text #3

Max Range: 1.9457. Min Range: -1.9457

Max Act: 1.3879. Min Act: -0.0000

Data Index: 325604 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 1.9457. Min Range: -1.9457

Max Act: 1.3736. Min Act: -0.0000

Data Index: 71765 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 1.9457. Min Range: -1.9457

Max Act: 1.3305. Min Act: -0.0000

Data Index: 158375 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 1.9457. Min Range: -1.9457

Max Act: 1.3576. Min Act: -0.0000

Data Index: 55583 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 1.9457. Min Range: -1.9457

Max Act: 1.3590. Min Act: -0.0000

Data Index: 424116 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 1.9457. Min Range: -1.9457

Max Act: 1.2228. Min Act: -0.0000

Data Index: 841956 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 1.9457. Min Range: -1.9457

Max Act: 1.2070. Min Act: -0.0000

Data Index: 798307 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 1.9457. Min Range: -1.9457

Max Act: 1.1700. Min Act: -0.0000

Data Index: 851144 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 1.9457. Min Range: -1.9457

Max Act: 1.1825. Min Act: -0.0000

Data Index: 499331 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 1.9457. Min Range: -1.9457

Max Act: 1.2312. Min Act: -0.0000

Data Index: 365787 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 1.9457. Min Range: -1.9457

Max Act: 1.2321. Min Act: -0.0000

Data Index: 115799 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 1.9457. Min Range: -1.9457

Max Act: 1.2634. Min Act: -0.0000

Data Index: 1298209 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 1.9457. Min Range: -1.9457

Max Act: 1.1770. Min Act: -0.0000

Data Index: 1341586 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 1.9457. Min Range: -1.9457

Max Act: 1.1526. Min Act: -0.0000

Data Index: 523479 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 1.9457. Min Range: -1.9457

Max Act: 1.0798. Min Act: -0.0000

Data Index: 1358253 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 1.9457. Min Range: -1.9457

Max Act: 1.2060. Min Act: -0.0000

Data Index: 572005 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 1.9457. Min Range: -1.9457

Max Act: 1.1663. Min Act: -0.0000

Data Index: 80658 (C4 (Web Text))

Max Activating Token Index: 485