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

Dataset: The Pile

Neuron 1847 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.9405. Min Act: -0.0000

Data Index: 1617018 (The Pile)

Max Activating Token Index: 739

Text #1

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.8644. Min Act: -0.0000

Data Index: 305375 (The Pile)

Max Activating Token Index: 525

Text #2

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.7136. Min Act: -0.0000

Data Index: 835781 (The Pile)

Max Activating Token Index: 804

Text #3

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.9240. Min Act: -0.0000

Data Index: 1895740 (The Pile)

Max Activating Token Index: 557

Text #4

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.7934. Min Act: -0.0000

Data Index: 900451 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.9014. Min Act: -0.0000

Data Index: 1744099 (The Pile)

Max Activating Token Index: 253

Text #6

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.8880. Min Act: -0.0000

Data Index: 1180120 (The Pile)

Max Activating Token Index: 129

Text #7

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.8288. Min Act: -0.0000

Data Index: 1534943 (The Pile)

Max Activating Token Index: 642

Text #8

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.8557. Min Act: -0.0000

Data Index: 1279084 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.8236. Min Act: -0.0000

Data Index: 642372 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.7880. Min Act: -0.0000

Data Index: 1247702 (The Pile)

Max Activating Token Index: 368

Text #11

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.8033. Min Act: -0.0000

Data Index: 603836 (The Pile)

Max Activating Token Index: 797

Text #12

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.6745. Min Act: -0.0000

Data Index: 1565619 (The Pile)

Max Activating Token Index: 573

Text #13

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.6357. Min Act: -0.0000

Data Index: 433513 (The Pile)

Max Activating Token Index: 889

Text #14

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.7627. Min Act: -0.0000

Data Index: 392084 (The Pile)

Max Activating Token Index: 341

Text #15

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.7748. Min Act: -0.0000

Data Index: 1472377 (The Pile)

Max Activating Token Index: 291

Text #16

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.7903. Min Act: -0.0000

Data Index: 1061389 (The Pile)

Max Activating Token Index: 940

Text #17

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.7661. Min Act: -0.0000

Data Index: 614014 (The Pile)

Max Activating Token Index: 682

Text #18

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.6465. Min Act: -0.0000

Data Index: 1150284 (The Pile)

Max Activating Token Index: 440

Text #19

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.6513. Min Act: -0.0000

Data Index: 133811 (The Pile)

Max Activating Token Index: 211