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

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

Neuron 2516 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1215640 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.5147. Min Act: -0.0000

Data Index: 1184578 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1063188 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4823. Min Act: -0.0000

Data Index: 327385 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1049638 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4598. Min Act: -0.0000

Data Index: 415678 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4703. Min Act: -0.0000

Data Index: 968627 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4442. Min Act: -0.0000

Data Index: 738839 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4762. Min Act: -0.0000

Data Index: 390530 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4447. Min Act: -0.0000

Data Index: 671962 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4709. Min Act: -0.0000

Data Index: 1287425 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4404. Min Act: -0.0000

Data Index: 58242 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4342. Min Act: -0.0000

Data Index: 904096 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1306381 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4374. Min Act: -0.0000

Data Index: 390945 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4172. Min Act: -0.0000

Data Index: 736409 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4287. Min Act: -0.0000

Data Index: 889182 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4154. Min Act: -0.0000

Data Index: 864279 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4275. Min Act: -0.0000

Data Index: 1210705 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.5238. Min Range: -0.5238

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1025632 (C4 (Web Text))

Max Activating Token Index: 410