Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2824 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.6841. Min Act: -0.0001

Data Index: 1355916 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.6265. Min Act: -0.0001

Data Index: 983607 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.6232. Min Act: -0.0001

Data Index: 886593 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.6360. Min Act: -0.0001

Data Index: 592183 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5750. Min Act: -0.0001

Data Index: 56503 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.6245. Min Act: -0.0001

Data Index: 397511 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5885. Min Act: -0.0001

Data Index: 1299518 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5651. Min Act: -0.0001

Data Index: 808814 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5813. Min Act: -0.0001

Data Index: 6926 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.6000. Min Act: -0.0001

Data Index: 330931 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5957. Min Act: -0.0001

Data Index: 1270861 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5555. Min Act: -0.0001

Data Index: 392605 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5512. Min Act: -0.0000

Data Index: 518097 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5335. Min Act: -0.0001

Data Index: 671024 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5397. Min Act: -0.0001

Data Index: 1172305 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5300. Min Act: -0.0000

Data Index: 555346 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5278. Min Act: -0.0001

Data Index: 866165 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5908. Min Act: -0.0001

Data Index: 603617 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5398. Min Act: -0.0000

Data Index: 349860 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.6841. Min Range: -0.6841

Max Act: 0.5143. Min Act: -0.0000

Data Index: 514306 (C4 (Web Text))

Max Activating Token Index: 724