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

Dataset: The Pile

Neuron 4126 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: 1.1514. Min Range: -1.1514

Max Act: 1.0347. Min Act: -0.0000

Data Index: 249053 (The Pile)

Max Activating Token Index: 652

Text #1

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1620461 (The Pile)

Max Activating Token Index: 946

Text #2

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.0649. Min Act: -0.0000

Data Index: 1254127 (The Pile)

Max Activating Token Index: 777

Text #3

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.9743. Min Act: -0.0000

Data Index: 1266760 (The Pile)

Max Activating Token Index: 985

Text #4

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.0266. Min Act: -0.0000

Data Index: 218731 (The Pile)

Max Activating Token Index: 398

Text #5

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.8958. Min Act: -0.0000

Data Index: 869664 (The Pile)

Max Activating Token Index: 895

Text #6

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.8943. Min Act: -0.0000

Data Index: 1739191 (The Pile)

Max Activating Token Index: 991

Text #7

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.0107. Min Act: -0.0000

Data Index: 1892123 (The Pile)

Max Activating Token Index: 245

Text #8

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.9976. Min Act: -0.0000

Data Index: 433719 (The Pile)

Max Activating Token Index: 838

Text #9

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.9739. Min Act: -0.0000

Data Index: 1658390 (The Pile)

Max Activating Token Index: 702

Text #10

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.9459. Min Act: -0.0000

Data Index: 870961 (The Pile)

Max Activating Token Index: 268

Text #11

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1813324 (The Pile)

Max Activating Token Index: 396

Text #12

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.1514. Min Act: -0.0000

Data Index: 919230 (The Pile)

Max Activating Token Index: 994

Text #13

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1592894 (The Pile)

Max Activating Token Index: 201

Text #14

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.8482. Min Act: -0.0000

Data Index: 1195843 (The Pile)

Max Activating Token Index: 584

Text #15

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.8984. Min Act: -0.0000

Data Index: 1124577 (The Pile)

Max Activating Token Index: 280

Text #16

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.8250. Min Act: -0.0000

Data Index: 1320219 (The Pile)

Max Activating Token Index: 713

Text #17

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.8716. Min Act: -0.0000

Data Index: 536981 (The Pile)

Max Activating Token Index: 602

Text #18

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.8317. Min Act: -0.0000

Data Index: 1126104 (The Pile)

Max Activating Token Index: 58

Text #19

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.8584. Min Act: -0.0000

Data Index: 407038 (The Pile)

Max Activating Token Index: 446