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

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

Neuron 1184 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: 2.1456. Min Range: -2.1456

Max Act: 2.1456. Min Act: -0.0000

Data Index: 197117 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 2.1456. Min Range: -2.1456

Max Act: 1.9789. Min Act: -0.0000

Data Index: 498570 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 2.1456. Min Range: -2.1456

Max Act: 1.9578. Min Act: -0.0000

Data Index: 364186 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 2.1456. Min Range: -2.1456

Max Act: 1.6556. Min Act: -0.0000

Data Index: 1234115 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 2.1456. Min Range: -2.1456

Max Act: 1.4622. Min Act: -0.0000

Data Index: 832563 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 2.1456. Min Range: -2.1456

Max Act: 1.5918. Min Act: -0.0000

Data Index: 1293950 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 2.1456. Min Range: -2.1456

Max Act: 1.6418. Min Act: -0.0000

Data Index: 863207 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 2.1456. Min Range: -2.1456

Max Act: 1.5430. Min Act: -0.0000

Data Index: 1348592 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 2.1456. Min Range: -2.1456

Max Act: 1.4143. Min Act: -0.0000

Data Index: 566752 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 2.1456. Min Range: -2.1456

Max Act: 1.4750. Min Act: -0.0000

Data Index: 249772 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 2.1456. Min Range: -2.1456

Max Act: 1.3575. Min Act: -0.0000

Data Index: 690469 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 2.1456. Min Range: -2.1456

Max Act: 1.3415. Min Act: -0.0000

Data Index: 123161 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 2.1456. Min Range: -2.1456

Max Act: 1.2762. Min Act: -0.0000

Data Index: 1029634 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 2.1456. Min Range: -2.1456

Max Act: 1.1930. Min Act: -0.0000

Data Index: 212696 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 2.1456. Min Range: -2.1456

Max Act: 1.2714. Min Act: -0.0000

Data Index: 1163160 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 2.1456. Min Range: -2.1456

Max Act: 1.2526. Min Act: -0.0000

Data Index: 742257 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 2.1456. Min Range: -2.1456

Max Act: 1.3161. Min Act: -0.0000

Data Index: 730305 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 2.1456. Min Range: -2.1456

Max Act: 1.2442. Min Act: -0.0000

Data Index: 370355 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 2.1456. Min Range: -2.1456

Max Act: 1.2324. Min Act: -0.0000

Data Index: 1098029 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 2.1456. Min Range: -2.1456

Max Act: 1.1602. Min Act: -0.0000

Data Index: 103781 (C4 (Web Text))

Max Activating Token Index: 153