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

Dataset: The Pile

Neuron 2185 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1102. Min Range: -1.1102

Max Act: 1.1102. Min Act: -0.0000

Data Index: 1899031 (The Pile)

Max Activating Token Index: 201

Text #1

Max Range: 1.1102. Min Range: -1.1102

Max Act: 1.1024. Min Act: -0.0000

Data Index: 1503339 (The Pile)

Max Activating Token Index: 535

Text #2

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.9095. Min Act: -0.0000

Data Index: 182253 (The Pile)

Max Activating Token Index: 832

Text #3

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.9886. Min Act: -0.0000

Data Index: 695034 (The Pile)

Max Activating Token Index: 330

Text #4

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.9267. Min Act: -0.0000

Data Index: 1339818 (The Pile)

Max Activating Token Index: 547

Text #5

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.9983. Min Act: -0.0000

Data Index: 15673 (The Pile)

Max Activating Token Index: 508

Text #6

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.9049. Min Act: -0.0000

Data Index: 1985940 (The Pile)

Max Activating Token Index: 396

Text #7

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1939411 (The Pile)

Max Activating Token Index: 121

Text #8

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1833128 (The Pile)

Max Activating Token Index: 347

Text #9

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.8199. Min Act: -0.0000

Data Index: 413728 (The Pile)

Max Activating Token Index: 997

Text #10

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.8562. Min Act: -0.0000

Data Index: 1398453 (The Pile)

Max Activating Token Index: 804

Text #11

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.8587. Min Act: -0.0000

Data Index: 169692 (The Pile)

Max Activating Token Index: 672

Text #12

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.8111. Min Act: -0.0000

Data Index: 170493 (The Pile)

Max Activating Token Index: 398

Text #13

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.8307. Min Act: -0.0000

Data Index: 1274230 (The Pile)

Max Activating Token Index: 408

Text #14

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1325823 (The Pile)

Max Activating Token Index: 77

Text #15

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1880254 (The Pile)

Max Activating Token Index: 390

Text #16

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.7677. Min Act: -0.0000

Data Index: 423785 (The Pile)

Max Activating Token Index: 342

Text #17

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.7577. Min Act: -0.0000

Data Index: 1013843 (The Pile)

Max Activating Token Index: 506

Text #18

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.8234. Min Act: -0.0000

Data Index: 1348085 (The Pile)

Max Activating Token Index: 464

Text #19

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.8477. Min Act: -0.0000

Data Index: 251836 (The Pile)

Max Activating Token Index: 857