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

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

Neuron 647 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: 0.7486. Min Range: -0.7486

Max Act: 0.7486. Min Act: -0.0000

Data Index: 1486813 (Python Code)

Max Activating Token Index: 3

Text #1

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.6708. Min Act: -0.0000

Data Index: 547913 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1247213 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1339361 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.6248. Min Act: -0.0000

Data Index: 70430 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1270840 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.6448. Min Act: -0.0000

Data Index: 872429 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5763. Min Act: -0.0000

Data Index: 974235 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.6555. Min Act: -0.0000

Data Index: 310969 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1266457 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1009942 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1117023 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5605. Min Act: -0.0000

Data Index: 701805 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5480. Min Act: -0.0000

Data Index: 1265478 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5492. Min Act: -0.0000

Data Index: 592550 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5331. Min Act: -0.0000

Data Index: 678233 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5272. Min Act: -0.0000

Data Index: 625499 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.4861. Min Act: -0.0000

Data Index: 508940 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5751. Min Act: -0.0000

Data Index: 373140 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5039. Min Act: -0.0000

Data Index: 378055 (C4 (Web Text))

Max Activating Token Index: 705