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

Dataset: The Pile

Neuron 2097 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1269442 (The Pile)

Max Activating Token Index: 678

Text #1

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1155980 (The Pile)

Max Activating Token Index: 764

Text #2

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5716. Min Act: -0.0000

Data Index: 1071976 (The Pile)

Max Activating Token Index: 453

Text #3

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1613720 (The Pile)

Max Activating Token Index: 551

Text #4

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1702150 (The Pile)

Max Activating Token Index: 588

Text #5

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5193. Min Act: -0.0000

Data Index: 793215 (The Pile)

Max Activating Token Index: 474

Text #6

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1933747 (The Pile)

Max Activating Token Index: 287

Text #7

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5023. Min Act: -0.0000

Data Index: 851953 (The Pile)

Max Activating Token Index: 384

Text #8

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5142. Min Act: -0.0000

Data Index: 599636 (The Pile)

Max Activating Token Index: 562

Text #9

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4972. Min Act: -0.0000

Data Index: 92598 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4986. Min Act: -0.0000

Data Index: 541122 (The Pile)

Max Activating Token Index: 895

Text #11

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1897621 (The Pile)

Max Activating Token Index: 958

Text #12

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4432. Min Act: -0.0000

Data Index: 1797948 (The Pile)

Max Activating Token Index: 902

Text #13

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5070. Min Act: -0.0000

Data Index: 133379 (The Pile)

Max Activating Token Index: 215

Text #14

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1957672 (The Pile)

Max Activating Token Index: 225

Text #15

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5245. Min Act: -0.0000

Data Index: 667138 (The Pile)

Max Activating Token Index: 357

Text #16

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4455. Min Act: -0.0000

Data Index: 159367 (The Pile)

Max Activating Token Index: 219

Text #17

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4407. Min Act: -0.0000

Data Index: 907215 (The Pile)

Max Activating Token Index: 668

Text #18

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4327. Min Act: -0.0000

Data Index: 407525 (The Pile)

Max Activating Token Index: 600

Text #19

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1018578 (The Pile)

Max Activating Token Index: 889