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

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

Neuron 2012 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: 0.4512. Min Range: -0.4512

Max Act: 0.4512. Min Act: -0.0000

Data Index: 1047916 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3998. Min Act: -0.0000

Data Index: 822614 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3745. Min Act: -0.0000

Data Index: 252811 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3814. Min Act: -0.0000

Data Index: 635560 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3293. Min Act: -0.0000

Data Index: 17139 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1045698 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3147. Min Act: -0.0000

Data Index: 473350 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3247. Min Act: -0.0000

Data Index: 654808 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3323. Min Act: -0.0000

Data Index: 1354823 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3135. Min Act: -0.0000

Data Index: 456943 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3126. Min Act: -0.0000

Data Index: 313863 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3238. Min Act: -0.0000

Data Index: 225872 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3084. Min Act: -0.0000

Data Index: 1344222 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2844. Min Act: -0.0000

Data Index: 970804 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3092. Min Act: -0.0000

Data Index: 658159 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2881. Min Act: -0.0000

Data Index: 48146 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2794. Min Act: -0.0000

Data Index: 1126197 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2868. Min Act: -0.0000

Data Index: 416435 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2979. Min Act: -0.0000

Data Index: 29299 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3147. Min Act: -0.0000

Data Index: 215107 (C4 (Web Text))

Max Activating Token Index: 979