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

Dataset: The Pile

Neuron 3872 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: 1.6964. Min Range: -1.6964

Max Act: 1.6964. Min Act: -0.0000

Data Index: 1475862 (The Pile)

Max Activating Token Index: 32

Text #1

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.5134. Min Act: -0.0000

Data Index: 1973035 (The Pile)

Max Activating Token Index: 930

Text #2

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.3188. Min Act: -0.0000

Data Index: 885646 (The Pile)

Max Activating Token Index: 569

Text #3

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.3689. Min Act: -0.0000

Data Index: 1889880 (The Pile)

Max Activating Token Index: 7

Text #4

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.4319. Min Act: -0.0000

Data Index: 921589 (The Pile)

Max Activating Token Index: 175

Text #5

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.3566. Min Act: -0.0000

Data Index: 1760598 (The Pile)

Max Activating Token Index: 948

Text #6

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.3403. Min Act: -0.0000

Data Index: 1932228 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.2166. Min Act: -0.0000

Data Index: 217966 (The Pile)

Max Activating Token Index: 220

Text #8

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.3345. Min Act: -0.0000

Data Index: 313711 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.2528. Min Act: -0.0000

Data Index: 933572 (The Pile)

Max Activating Token Index: 817

Text #10

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.2581. Min Act: -0.0000

Data Index: 1863116 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.1294. Min Act: -0.0000

Data Index: 392471 (The Pile)

Max Activating Token Index: 128

Text #12

Max Range: 1.6964. Min Range: -1.6964

Max Act: 0.9895. Min Act: -0.0000

Data Index: 756497 (The Pile)

Max Activating Token Index: 864

Text #13

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.1792. Min Act: -0.0000

Data Index: 1092060 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.1605. Min Act: -0.0000

Data Index: 1926078 (The Pile)

Max Activating Token Index: 685

Text #15

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.1491. Min Act: -0.0000

Data Index: 822435 (The Pile)

Max Activating Token Index: 270

Text #16

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.0936. Min Act: -0.0000

Data Index: 763006 (The Pile)

Max Activating Token Index: 32

Text #17

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.1604. Min Act: -0.0000

Data Index: 126676 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.1483. Min Act: -0.0000

Data Index: 1054518 (The Pile)

Max Activating Token Index: 471

Text #19

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.1551. Min Act: -0.0000

Data Index: 1063070 (The Pile)

Max Activating Token Index: 763