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

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

Neuron 408 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1006. Min Range: -3.1006

Max Act: 3.1006. Min Act: -0.0001

Data Index: 649717 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 3.1006. Min Range: -3.1006

Max Act: 3.0660. Min Act: -0.0001

Data Index: 807014 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.8621. Min Act: -0.0001

Data Index: 569586 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.8382. Min Act: -0.0001

Data Index: 402436 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.8043. Min Act: -0.0001

Data Index: 127072 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9317. Min Act: -0.0001

Data Index: 496587 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9243. Min Act: -0.0001

Data Index: 514480 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 3.1006. Min Range: -3.1006

Max Act: 3.0518. Min Act: -0.0001

Data Index: 864717 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9189. Min Act: -0.0001

Data Index: 543688 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9106. Min Act: -0.0001

Data Index: 630327 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 3.1006. Min Range: -3.1006

Max Act: 3.0653. Min Act: -0.0001

Data Index: 537223 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.7522. Min Act: -0.0001

Data Index: 86146 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 3.1006. Min Range: -3.1006

Max Act: 3.0302. Min Act: -0.0001

Data Index: 585378 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.8859. Min Act: -0.0001

Data Index: 472090 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 3.1006. Min Range: -3.1006

Max Act: 3.0301. Min Act: -0.0001

Data Index: 73942 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.7346. Min Act: -0.0001

Data Index: 898473 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.6164. Min Act: -0.0001

Data Index: 483304 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.7206. Min Act: -0.0001

Data Index: 832235 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.8411. Min Act: -0.0001

Data Index: 954067 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.8329. Min Act: -0.0001

Data Index: 290830 (C4 (Web Text))

Max Activating Token Index: 464