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

Dataset: The Pile

Neuron 3951 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.7132. Min Act: -0.0000

Data Index: 1147468 (The Pile)

Max Activating Token Index: 505

Text #1

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.5335. Min Act: -0.0000

Data Index: 1029123 (The Pile)

Max Activating Token Index: 307

Text #2

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.4780. Min Act: -0.0000

Data Index: 1260136 (The Pile)

Max Activating Token Index: 619

Text #3

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.2309. Min Act: -0.0000

Data Index: 653406 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.3273. Min Act: -0.0000

Data Index: 465596 (The Pile)

Max Activating Token Index: 756

Text #5

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.4061. Min Act: -0.0000

Data Index: 85248 (The Pile)

Max Activating Token Index: 715

Text #6

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.4433. Min Act: -0.0000

Data Index: 207520 (The Pile)

Max Activating Token Index: 846

Text #7

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.2504. Min Act: -0.0000

Data Index: 907317 (The Pile)

Max Activating Token Index: 537

Text #8

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.3952. Min Act: -0.0000

Data Index: 1900018 (The Pile)

Max Activating Token Index: 227

Text #9

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.2737. Min Act: -0.0000

Data Index: 1344780 (The Pile)

Max Activating Token Index: 342

Text #10

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.2164. Min Act: -0.0000

Data Index: 1661180 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.3340. Min Act: -0.0000

Data Index: 541874 (The Pile)

Max Activating Token Index: 576

Text #12

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.3002. Min Act: -0.0000

Data Index: 845648 (The Pile)

Max Activating Token Index: 477

Text #13

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.2758. Min Act: -0.0000

Data Index: 398991 (The Pile)

Max Activating Token Index: 508

Text #14

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.2012. Min Act: -0.0000

Data Index: 1475148 (The Pile)

Max Activating Token Index: 975

Text #15

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.2988. Min Act: -0.0000

Data Index: 453361 (The Pile)

Max Activating Token Index: 276

Text #16

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.2542. Min Act: -0.0000

Data Index: 909992 (The Pile)

Max Activating Token Index: 985

Text #17

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.2238. Min Act: -0.0000

Data Index: 1088632 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.2633. Min Act: -0.0000

Data Index: 914273 (The Pile)

Max Activating Token Index: 511

Text #19

Max Range: 1.7132. Min Range: -1.7132

Max Act: 1.2878. Min Act: -0.0000

Data Index: 147121 (The Pile)

Max Activating Token Index: 787