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

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

Neuron 3731 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: 2.1471. Min Range: -2.1471

Max Act: 2.1471. Min Act: -0.0000

Data Index: 551417 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 2.1471. Min Range: -2.1471

Max Act: 2.0287. Min Act: -0.0000

Data Index: 1324045 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 2.1471. Min Range: -2.1471

Max Act: 2.0114. Min Act: -0.0000

Data Index: 769270 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.8789. Min Act: -0.0000

Data Index: 521548 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.8872. Min Act: -0.0000

Data Index: 1192108 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.8159. Min Act: -0.0000

Data Index: 929887 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.8878. Min Act: -0.0000

Data Index: 933356 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.7816. Min Act: -0.0000

Data Index: 901760 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.6533. Min Act: -0.0000

Data Index: 51310 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.7104. Min Act: -0.0000

Data Index: 438519 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.7805. Min Act: -0.0000

Data Index: 618437 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.6481. Min Act: -0.0000

Data Index: 384410 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.6409. Min Act: -0.0000

Data Index: 876156 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.6400. Min Act: -0.0000

Data Index: 157154 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.5259. Min Act: -0.0000

Data Index: 588613 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.6242. Min Act: -0.0000

Data Index: 1333327 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.6358. Min Act: -0.0000

Data Index: 17564 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.5752. Min Act: -0.0000

Data Index: 963948 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.5776. Min Act: -0.0000

Data Index: 13697 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.4900. Min Act: -0.0000

Data Index: 500781 (C4 (Web Text))

Max Activating Token Index: 603