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

Dataset: The Pile

Neuron 4474 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.5946. Min Act: -0.0000

Data Index: 1929431 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.5150. Min Act: -0.0000

Data Index: 282716 (The Pile)

Max Activating Token Index: 308

Text #2

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.4957. Min Act: -0.0000

Data Index: 553586 (The Pile)

Max Activating Token Index: 374

Text #3

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.4864. Min Act: -0.0000

Data Index: 118631 (The Pile)

Max Activating Token Index: 97

Text #4

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.4590. Min Act: -0.0000

Data Index: 1799321 (The Pile)

Max Activating Token Index: 86

Text #5

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.3148. Min Act: -0.0000

Data Index: 400341 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.1322. Min Act: -0.0000

Data Index: 1839067 (The Pile)

Max Activating Token Index: 1002

Text #7

Max Range: 3.5946. Min Range: -3.5946

Max Act: 2.8357. Min Act: -0.0000

Data Index: 426089 (The Pile)

Max Activating Token Index: 658

Text #8

Max Range: 3.5946. Min Range: -3.5946

Max Act: 3.1721. Min Act: -0.0000

Data Index: 1308857 (The Pile)

Max Activating Token Index: 601

Text #9

Max Range: 3.5946. Min Range: -3.5946

Max Act: 2.8242. Min Act: -0.0000

Data Index: 790600 (The Pile)

Max Activating Token Index: 200

Text #10

Max Range: 3.5946. Min Range: -3.5946

Max Act: 2.4679. Min Act: -0.0000

Data Index: 1428694 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 3.5946. Min Range: -3.5946

Max Act: 2.8543. Min Act: -0.0000

Data Index: 1895013 (The Pile)

Max Activating Token Index: 884

Text #12

Max Range: 3.5946. Min Range: -3.5946

Max Act: 2.8296. Min Act: -0.0000

Data Index: 390694 (The Pile)

Max Activating Token Index: 569

Text #13

Max Range: 3.5946. Min Range: -3.5946

Max Act: 2.6701. Min Act: -0.0000

Data Index: 40018 (The Pile)

Max Activating Token Index: 393

Text #14

Max Range: 3.5946. Min Range: -3.5946

Max Act: 2.7994. Min Act: -0.0000

Data Index: 211414 (The Pile)

Max Activating Token Index: 233

Text #15

Max Range: 3.5946. Min Range: -3.5946

Max Act: 2.7990. Min Act: -0.0000

Data Index: 1782520 (The Pile)

Max Activating Token Index: 354

Text #16

Max Range: 3.5946. Min Range: -3.5946

Max Act: 2.2575. Min Act: -0.0000

Data Index: 1650633 (The Pile)

Max Activating Token Index: 127

Text #17

Max Range: 3.5946. Min Range: -3.5946

Max Act: 2.4709. Min Act: -0.0000

Data Index: 532095 (The Pile)

Max Activating Token Index: 374

Text #18

Max Range: 3.5946. Min Range: -3.5946

Max Act: 2.2913. Min Act: -0.0000

Data Index: 1364004 (The Pile)

Max Activating Token Index: 707

Text #19

Max Range: 3.5946. Min Range: -3.5946

Max Act: 2.4233. Min Act: -0.0000

Data Index: 1574741 (The Pile)

Max Activating Token Index: 399