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

Dataset: The Pile

Neuron 3465 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0075. Min Range: -1.0075

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1667314 (The Pile)

Max Activating Token Index: 818

Text #1

Max Range: 1.0075. Min Range: -1.0075

Max Act: 0.8347. Min Act: -0.0000

Data Index: 56576 (The Pile)

Max Activating Token Index: 179

Text #2

Max Range: 1.0075. Min Range: -1.0075

Max Act: 0.8247. Min Act: -0.0000

Data Index: 793019 (The Pile)

Max Activating Token Index: 380

Text #3

Max Range: 1.0075. Min Range: -1.0075

Max Act: 0.6526. Min Act: -0.0000

Data Index: 850243 (The Pile)

Max Activating Token Index: 985

Text #4

Max Range: 1.0075. Min Range: -1.0075

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1792491 (The Pile)

Max Activating Token Index: 608

Text #5

Max Range: 1.0075. Min Range: -1.0075

Max Act: 0.7276. Min Act: -0.0000

Data Index: 221675 (The Pile)

Max Activating Token Index: 766

Text #6

Max Range: 1.0075. Min Range: -1.0075

Max Act: 0.7089. Min Act: -0.0000

Data Index: 283396 (The Pile)

Max Activating Token Index: 980

Text #7

Max Range: 1.0075. Min Range: -1.0075

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1467583 (The Pile)

Max Activating Token Index: 153

Text #8

Max Range: 1.0075. Min Range: -1.0075

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1814861 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 1.0075. Min Range: -1.0075

Max Act: 0.6417. Min Act: -0.0000

Data Index: 943192 (The Pile)

Max Activating Token Index: 881

Text #10

Max Range: 1.0075. Min Range: -1.0075

Max Act: 0.6794. Min Act: -0.0000

Data Index: 1732741 (The Pile)

Max Activating Token Index: 454

Text #11

Max Range: 1.0075. Min Range: -1.0075

Max Act: 0.6123. Min Act: -0.0000

Data Index: 28440 (The Pile)

Max Activating Token Index: 394

Text #12

Max Range: 1.0075. Min Range: -1.0075

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1748554 (The Pile)

Max Activating Token Index: 254

Text #13

Max Range: 1.0075. Min Range: -1.0075

Max Act: 0.5802. Min Act: -0.0000

Data Index: 1006909 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 1.0075. Min Range: -1.0075

Max Act: 0.5568. Min Act: -0.0000

Data Index: 730149 (The Pile)

Max Activating Token Index: 769

Text #15

Max Range: 1.0075. Min Range: -1.0075

Max Act: 0.6041. Min Act: -0.0000

Data Index: 496725 (The Pile)

Max Activating Token Index: 144

Text #16

Max Range: 1.0075. Min Range: -1.0075

Max Act: 0.6133. Min Act: -0.0000

Data Index: 896632 (The Pile)

Max Activating Token Index: 496

Text #17

Max Range: 1.0075. Min Range: -1.0075

Max Act: 0.6128. Min Act: -0.0000

Data Index: 446646 (The Pile)

Max Activating Token Index: 835

Text #18

Max Range: 1.0075. Min Range: -1.0075

Max Act: 0.5769. Min Act: -0.0000

Data Index: 116499 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 1.0075. Min Range: -1.0075

Max Act: 0.5520. Min Act: -0.0000

Data Index: 220317 (The Pile)

Max Activating Token Index: 79