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

Dataset: The Pile

Neuron 3410 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.7570. Min Act: -0.0000

Data Index: 539491 (The Pile)

Max Activating Token Index: 242

Text #1

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1206396 (The Pile)

Max Activating Token Index: 868

Text #2

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1087871 (The Pile)

Max Activating Token Index: 313

Text #3

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1223870 (The Pile)

Max Activating Token Index: 369

Text #4

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6503. Min Act: -0.0000

Data Index: 747374 (The Pile)

Max Activating Token Index: 694

Text #5

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5758. Min Act: -0.0000

Data Index: 28873 (The Pile)

Max Activating Token Index: 465

Text #6

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6323. Min Act: -0.0000

Data Index: 1072957 (The Pile)

Max Activating Token Index: 348

Text #7

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6074. Min Act: -0.0000

Data Index: 1474146 (The Pile)

Max Activating Token Index: 431

Text #8

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1597851 (The Pile)

Max Activating Token Index: 757

Text #9

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5305. Min Act: -0.0000

Data Index: 638523 (The Pile)

Max Activating Token Index: 474

Text #10

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5855. Min Act: -0.0000

Data Index: 807380 (The Pile)

Max Activating Token Index: 672

Text #11

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5912. Min Act: -0.0000

Data Index: 1346916 (The Pile)

Max Activating Token Index: 129

Text #12

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5871. Min Act: -0.0000

Data Index: 68469 (The Pile)

Max Activating Token Index: 223

Text #13

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1399489 (The Pile)

Max Activating Token Index: 723

Text #14

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.4921. Min Act: -0.0000

Data Index: 1505181 (The Pile)

Max Activating Token Index: 101

Text #15

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5092. Min Act: -0.0000

Data Index: 339583 (The Pile)

Max Activating Token Index: 210

Text #16

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5740. Min Act: -0.0000

Data Index: 1754451 (The Pile)

Max Activating Token Index: 128

Text #17

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1740065 (The Pile)

Max Activating Token Index: 351

Text #18

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5436. Min Act: -0.0000

Data Index: 896416 (The Pile)

Max Activating Token Index: 821

Text #19

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1889456 (The Pile)

Max Activating Token Index: 326