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

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

Neuron 3864 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: 4.6414. Min Range: -4.6414

Max Act: 4.6414. Min Act: -0.0000

Data Index: 629003 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 4.6414. Min Range: -4.6414

Max Act: 4.6170. Min Act: -0.0000

Data Index: 1322409 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 4.6414. Min Range: -4.6414

Max Act: 3.9488. Min Act: -0.0000

Data Index: 889700 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 4.6414. Min Range: -4.6414

Max Act: 3.7593. Min Act: -0.0000

Data Index: 1036253 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 4.6414. Min Range: -4.6414

Max Act: 3.5139. Min Act: -0.0000

Data Index: 5809 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 4.6414. Min Range: -4.6414

Max Act: 3.2728. Min Act: -0.0000

Data Index: 1337574 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 4.6414. Min Range: -4.6414

Max Act: 3.2797. Min Act: -0.0000

Data Index: 1278862 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 4.6414. Min Range: -4.6414

Max Act: 3.1086. Min Act: -0.0000

Data Index: 368747 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 4.6414. Min Range: -4.6414

Max Act: 3.2061. Min Act: -0.0000

Data Index: 281679 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 4.6414. Min Range: -4.6414

Max Act: 3.1917. Min Act: -0.0000

Data Index: 51361 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 4.6414. Min Range: -4.6414

Max Act: 3.0432. Min Act: -0.0000

Data Index: 725397 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 4.6414. Min Range: -4.6414

Max Act: 3.0292. Min Act: -0.0000

Data Index: 1323608 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 4.6414. Min Range: -4.6414

Max Act: 3.0270. Min Act: -0.0000

Data Index: 486064 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 4.6414. Min Range: -4.6414

Max Act: 2.4686. Min Act: -0.0000

Data Index: 719043 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 4.6414. Min Range: -4.6414

Max Act: 2.8079. Min Act: -0.0000

Data Index: 64209 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 4.6414. Min Range: -4.6414

Max Act: 2.9054. Min Act: -0.0000

Data Index: 65654 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 4.6414. Min Range: -4.6414

Max Act: 2.8990. Min Act: -0.0000

Data Index: 747788 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 4.6414. Min Range: -4.6414

Max Act: 2.8626. Min Act: -0.0000

Data Index: 312087 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 4.6414. Min Range: -4.6414

Max Act: 2.9929. Min Act: -0.0000

Data Index: 627704 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 4.6414. Min Range: -4.6414

Max Act: 2.9755. Min Act: -0.0000

Data Index: 529511 (C4 (Web Text))

Max Activating Token Index: 72