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

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

Neuron 122 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.5892. Min Act: -0.0000

Data Index: 545914 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 2.0614. Min Range: -2.0614

Max Act: 2.0614. Min Act: -0.0000

Data Index: 1357514 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.7018. Min Act: -0.0000

Data Index: 378979 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.4871. Min Act: -0.0000

Data Index: 1149994 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.5578. Min Act: -0.0000

Data Index: 381669 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.5855. Min Act: -0.0001

Data Index: 1189390 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.7293. Min Act: -0.0000

Data Index: 1273420 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.6821. Min Act: -0.0000

Data Index: 1314213 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.5454. Min Act: -0.0000

Data Index: 728813 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.5641. Min Act: -0.0000

Data Index: 356682 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.6579. Min Act: -0.0000

Data Index: 169128 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.3431. Min Act: -0.0000

Data Index: 329770 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.6376. Min Act: -0.0000

Data Index: 166810 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.6176. Min Act: -0.0000

Data Index: 460540 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.4311. Min Act: -0.0000

Data Index: 1089638 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.3517. Min Act: -0.0000

Data Index: 1179437 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.3428. Min Act: -0.0000

Data Index: 571482 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.3769. Min Act: -0.0001

Data Index: 674121 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.3869. Min Act: -0.0001

Data Index: 253302 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 2.0614. Min Range: -2.0614

Max Act: 1.3455. Min Act: -0.0000

Data Index: 898394 (C4 (Web Text))

Max Activating Token Index: 991