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

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

Neuron 3897 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: 1.4951. Min Range: -1.4951

Max Act: 1.3388. Min Act: -0.0000

Data Index: 275842 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.4951. Min Act: -0.0000

Data Index: 1356339 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.1835. Min Act: -0.0000

Data Index: 847980 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.1279. Min Act: -0.0000

Data Index: 1032847 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.1408. Min Act: -0.0000

Data Index: 248593 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 1.4951. Min Range: -1.4951

Max Act: 0.9961. Min Act: -0.0000

Data Index: 325021 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.0659. Min Act: -0.0000

Data Index: 114204 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.0554. Min Act: -0.0000

Data Index: 1010033 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.0740. Min Act: -0.0000

Data Index: 33456 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 1.4951. Min Range: -1.4951

Max Act: 0.9158. Min Act: -0.0000

Data Index: 1123653 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 1.4951. Min Range: -1.4951

Max Act: 0.9133. Min Act: -0.0000

Data Index: 1509267 (Python Code)

Max Activating Token Index: 364

Text #11

Max Range: 1.4951. Min Range: -1.4951

Max Act: 0.7914. Min Act: -0.0000

Data Index: 455387 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 1.4951. Min Range: -1.4951

Max Act: 0.8201. Min Act: -0.0000

Data Index: 42505 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 1.4951. Min Range: -1.4951

Max Act: 0.8410. Min Act: -0.0000

Data Index: 658067 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 1.4951. Min Range: -1.4951

Max Act: 0.8300. Min Act: -0.0000

Data Index: 468037 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 1.4951. Min Range: -1.4951

Max Act: 0.8152. Min Act: -0.0000

Data Index: 1192941 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 1.4951. Min Range: -1.4951

Max Act: 0.9262. Min Act: -0.0000

Data Index: 475368 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 1.4951. Min Range: -1.4951

Max Act: 0.7230. Min Act: -0.0000

Data Index: 405662 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 1.4951. Min Range: -1.4951

Max Act: 0.7227. Min Act: -0.0000

Data Index: 1230709 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 1.4951. Min Range: -1.4951

Max Act: 0.8008. Min Act: -0.0000

Data Index: 166749 (C4 (Web Text))

Max Activating Token Index: 522