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

Dataset: The Pile

Neuron 984 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.9521. Min Act: -0.0000

Data Index: 1682813 (The Pile)

Max Activating Token Index: 413

Text #1

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.8753. Min Act: -0.0000

Data Index: 954400 (The Pile)

Max Activating Token Index: 253

Text #2

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.8856. Min Act: -0.0000

Data Index: 311407 (The Pile)

Max Activating Token Index: 769

Text #3

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.8084. Min Act: -0.0000

Data Index: 351525 (The Pile)

Max Activating Token Index: 37

Text #4

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1129512 (The Pile)

Max Activating Token Index: 60

Text #5

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1285128 (The Pile)

Max Activating Token Index: 829

Text #6

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.6754. Min Act: 0.0001

Data Index: 1698028 (The Pile)

Max Activating Token Index: 808

Text #7

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.8629. Min Act: -0.0000

Data Index: 795828 (The Pile)

Max Activating Token Index: 646

Text #8

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1500650 (The Pile)

Max Activating Token Index: 664

Text #9

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1130267 (The Pile)

Max Activating Token Index: 756

Text #10

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.6962. Min Act: -0.0000

Data Index: 1211716 (The Pile)

Max Activating Token Index: 322

Text #11

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.6235. Min Act: -0.0001

Data Index: 1538812 (The Pile)

Max Activating Token Index: 224

Text #12

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1515735 (The Pile)

Max Activating Token Index: 492

Text #13

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1821496 (The Pile)

Max Activating Token Index: 471

Text #14

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1262114 (The Pile)

Max Activating Token Index: 697

Text #15

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7007. Min Act: -0.0000

Data Index: 99589 (The Pile)

Max Activating Token Index: 483

Text #16

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1542279 (The Pile)

Max Activating Token Index: 457

Text #17

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.6645. Min Act: -0.0000

Data Index: 904423 (The Pile)

Max Activating Token Index: 729

Text #18

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.6393. Min Act: -0.0000

Data Index: 664862 (The Pile)

Max Activating Token Index: 227

Text #19

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1031827 (The Pile)

Max Activating Token Index: 211