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

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

Neuron 3391 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.8055. Min Act: -0.0001

Data Index: 215661 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.9353. Min Act: -0.0001

Data Index: 1340501 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.6782. Min Act: -0.0001

Data Index: 348338 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.6247. Min Act: -0.0002

Data Index: 1211939 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.4212. Min Act: -0.0002

Data Index: 1197302 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.4521. Min Act: -0.0002

Data Index: 312547 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.4548. Min Act: -0.0002

Data Index: 1332623 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.5103. Min Act: -0.0002

Data Index: 543435 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.4527. Min Act: -0.0002

Data Index: 1002522 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.2972. Min Act: -0.0001

Data Index: 673462 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.4239. Min Act: -0.0002

Data Index: 1179368 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.3764. Min Act: -0.0002

Data Index: 165806 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.1874. Min Act: -0.0002

Data Index: 904766 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.2262. Min Act: -0.0002

Data Index: 820104 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.4432. Min Act: -0.0002

Data Index: 774409 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.2370. Min Act: -0.0001

Data Index: 804825 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.3903. Min Act: -0.0001

Data Index: 1116541 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.3147. Min Act: -0.0002

Data Index: 456520 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.1690. Min Act: -0.0001

Data Index: 889376 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.1305. Min Act: -0.0002

Data Index: 337909 (C4 (Web Text))

Max Activating Token Index: 649