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

Dataset: The Pile

Neuron 3916 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3788. Min Act: -0.0000

Data Index: 737491 (The Pile)

Max Activating Token Index: 459

Text #1

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3548. Min Act: -0.0000

Data Index: 594175 (The Pile)

Max Activating Token Index: 129

Text #2

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3319. Min Act: -0.0000

Data Index: 934621 (The Pile)

Max Activating Token Index: 640

Text #3

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3520. Min Act: -0.0000

Data Index: 299974 (The Pile)

Max Activating Token Index: 205

Text #4

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2908. Min Act: -0.0000

Data Index: 1107869 (The Pile)

Max Activating Token Index: 812

Text #5

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2885. Min Act: -0.0000

Data Index: 1028023 (The Pile)

Max Activating Token Index: 106

Text #6

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1304720 (The Pile)

Max Activating Token Index: 336

Text #7

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1743295 (The Pile)

Max Activating Token Index: 430

Text #8

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2930. Min Act: -0.0000

Data Index: 582441 (The Pile)

Max Activating Token Index: 106

Text #9

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2990. Min Act: -0.0000

Data Index: 702904 (The Pile)

Max Activating Token Index: 912

Text #10

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2595. Min Act: -0.0001

Data Index: 1301063 (The Pile)

Max Activating Token Index: 570

Text #11

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2734. Min Act: -0.0000

Data Index: 424660 (The Pile)

Max Activating Token Index: 182

Text #12

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2795. Min Act: -0.0000

Data Index: 1846270 (The Pile)

Max Activating Token Index: 896

Text #13

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2698. Min Act: -0.0000

Data Index: 964452 (The Pile)

Max Activating Token Index: 517

Text #14

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2594. Min Act: -0.0000

Data Index: 1461007 (The Pile)

Max Activating Token Index: 440

Text #15

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1403462 (The Pile)

Max Activating Token Index: 79

Text #16

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1910281 (The Pile)

Max Activating Token Index: 725

Text #17

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1206528 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1512683 (The Pile)

Max Activating Token Index: 237

Text #19

Max Range: 0.3788. Min Range: -0.3788

Max Act: 0.2554. Min Act: -0.0000

Data Index: 608137 (The Pile)

Max Activating Token Index: 256