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

Dataset: The Pile

Neuron 823 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: 1.4397. Min Range: -1.4397

Max Act: 1.4397. Min Act: -0.0000

Data Index: 1906445 (The Pile)

Max Activating Token Index: 462

Text #1

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.9858. Min Act: -0.0000

Data Index: 1678540 (The Pile)

Max Activating Token Index: 709

Text #2

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.0415. Min Act: -0.0000

Data Index: 157595 (The Pile)

Max Activating Token Index: 714

Text #3

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.9227. Min Act: -0.0000

Data Index: 826661 (The Pile)

Max Activating Token Index: 309

Text #4

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.8808. Min Act: -0.0000

Data Index: 1050864 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.8429. Min Act: -0.0000

Data Index: 490559 (The Pile)

Max Activating Token Index: 904

Text #6

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.9708. Min Act: -0.0000

Data Index: 1254116 (The Pile)

Max Activating Token Index: 29

Text #7

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.8577. Min Act: -0.0000

Data Index: 474851 (The Pile)

Max Activating Token Index: 762

Text #8

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1817153 (The Pile)

Max Activating Token Index: 561

Text #9

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.8635. Min Act: -0.0000

Data Index: 558834 (The Pile)

Max Activating Token Index: 108

Text #10

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.8560. Min Act: -0.0000

Data Index: 544355 (The Pile)

Max Activating Token Index: 921

Text #11

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.8802. Min Act: -0.0000

Data Index: 1096906 (The Pile)

Max Activating Token Index: 950

Text #12

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1930299 (The Pile)

Max Activating Token Index: 524

Text #13

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.8536. Min Act: -0.0000

Data Index: 992665 (The Pile)

Max Activating Token Index: 73

Text #14

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.8023. Min Act: -0.0000

Data Index: 1020516 (The Pile)

Max Activating Token Index: 98

Text #15

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.8302. Min Act: -0.0000

Data Index: 275604 (The Pile)

Max Activating Token Index: 781

Text #16

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.8101. Min Act: -0.0000

Data Index: 1397390 (The Pile)

Max Activating Token Index: 989

Text #17

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.8646. Min Act: -0.0000

Data Index: 821234 (The Pile)

Max Activating Token Index: 738

Text #18

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.7954. Min Act: -0.0000

Data Index: 283945 (The Pile)

Max Activating Token Index: 671

Text #19

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.8440. Min Act: -0.0000

Data Index: 1167706 (The Pile)

Max Activating Token Index: 475