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

Dataset: The Pile

Neuron 2824 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 13.4498. Min Range: -13.4498

Max Act: 13.4498. Min Act: -0.0000

Data Index: 3283 (The Pile)

Max Activating Token Index: 804

Text #1

Max Range: 13.4498. Min Range: -13.4498

Max Act: 13.3879. Min Act: -0.0000

Data Index: 1694188 (The Pile)

Max Activating Token Index: 469

Text #2

Max Range: 13.4498. Min Range: -13.4498

Max Act: 13.3102. Min Act: -0.0000

Data Index: 515271 (The Pile)

Max Activating Token Index: 242

Text #3

Max Range: 13.4498. Min Range: -13.4498

Max Act: 12.9109. Min Act: -0.0000

Data Index: 656306 (The Pile)

Max Activating Token Index: 404

Text #4

Max Range: 13.4498. Min Range: -13.4498

Max Act: 13.1659. Min Act: -0.0000

Data Index: 152534 (The Pile)

Max Activating Token Index: 380

Text #5

Max Range: 13.4498. Min Range: -13.4498

Max Act: 12.6847. Min Act: -0.0000

Data Index: 1754895 (The Pile)

Max Activating Token Index: 688

Text #6

Max Range: 13.4498. Min Range: -13.4498

Max Act: 12.5645. Min Act: -0.0000

Data Index: 647453 (The Pile)

Max Activating Token Index: 239

Text #7

Max Range: 13.4498. Min Range: -13.4498

Max Act: 12.5876. Min Act: -0.0000

Data Index: 267756 (The Pile)

Max Activating Token Index: 172

Text #8

Max Range: 13.4498. Min Range: -13.4498

Max Act: 12.6575. Min Act: -0.0000

Data Index: 1315343 (The Pile)

Max Activating Token Index: 642

Text #9

Max Range: 13.4498. Min Range: -13.4498

Max Act: 12.5967. Min Act: -0.0000

Data Index: 740784 (The Pile)

Max Activating Token Index: 705

Text #10

Max Range: 13.4498. Min Range: -13.4498

Max Act: 12.5964. Min Act: -0.0000

Data Index: 426555 (The Pile)

Max Activating Token Index: 717

Text #11

Max Range: 13.4498. Min Range: -13.4498

Max Act: 12.7557. Min Act: -0.0000

Data Index: 785920 (The Pile)

Max Activating Token Index: 975

Text #12

Max Range: 13.4498. Min Range: -13.4498

Max Act: 12.6698. Min Act: -0.0000

Data Index: 1007383 (The Pile)

Max Activating Token Index: 630

Text #13

Max Range: 13.4498. Min Range: -13.4498

Max Act: 12.7466. Min Act: -0.0000

Data Index: 1054396 (The Pile)

Max Activating Token Index: 444

Text #14

Max Range: 13.4498. Min Range: -13.4498

Max Act: 12.6641. Min Act: -0.0000

Data Index: 1427059 (The Pile)

Max Activating Token Index: 226

Text #15

Max Range: 13.4498. Min Range: -13.4498

Max Act: 12.8206. Min Act: -0.0000

Data Index: 102674 (The Pile)

Max Activating Token Index: 948

Text #16

Max Range: 13.4498. Min Range: -13.4498

Max Act: 12.6964. Min Act: -0.0000

Data Index: 482358 (The Pile)

Max Activating Token Index: 837

Text #17

Max Range: 13.4498. Min Range: -13.4498

Max Act: 12.6677. Min Act: -0.0000

Data Index: 1679251 (The Pile)

Max Activating Token Index: 239

Text #18

Max Range: 13.4498. Min Range: -13.4498

Max Act: 12.8300. Min Act: -0.0000

Data Index: 1489815 (The Pile)

Max Activating Token Index: 829

Text #19

Max Range: 13.4498. Min Range: -13.4498

Max Act: 12.5831. Min Act: -0.0000

Data Index: 449500 (The Pile)

Max Activating Token Index: 458