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

Dataset: The Pile

Neuron 2566 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: 1.5523. Min Range: -1.5523

Max Act: 1.5523. Min Act: -0.0000

Data Index: 1756126 (The Pile)

Max Activating Token Index: 815

Text #1

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.3201. Min Act: -0.0000

Data Index: 1929536 (The Pile)

Max Activating Token Index: 44

Text #2

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.2776. Min Act: -0.0000

Data Index: 1620034 (The Pile)

Max Activating Token Index: 442

Text #3

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.3958. Min Act: -0.0000

Data Index: 801654 (The Pile)

Max Activating Token Index: 810

Text #4

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.3067. Min Act: -0.0000

Data Index: 1189748 (The Pile)

Max Activating Token Index: 103

Text #5

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.2521. Min Act: -0.0000

Data Index: 125180 (The Pile)

Max Activating Token Index: 745

Text #6

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.2064. Min Act: -0.0000

Data Index: 431264 (The Pile)

Max Activating Token Index: 151

Text #7

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.2108. Min Act: -0.0000

Data Index: 101946 (The Pile)

Max Activating Token Index: 554

Text #8

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.1388. Min Act: -0.0000

Data Index: 604717 (The Pile)

Max Activating Token Index: 499

Text #9

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.1942. Min Act: -0.0000

Data Index: 710411 (The Pile)

Max Activating Token Index: 803

Text #10

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.1981. Min Act: -0.0000

Data Index: 617825 (The Pile)

Max Activating Token Index: 171

Text #11

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.1229. Min Act: -0.0000

Data Index: 546017 (The Pile)

Max Activating Token Index: 165

Text #12

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.2521. Min Act: -0.0000

Data Index: 1339976 (The Pile)

Max Activating Token Index: 107

Text #13

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.1898. Min Act: -0.0000

Data Index: 159304 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.1826. Min Act: -0.0000

Data Index: 1863076 (The Pile)

Max Activating Token Index: 342

Text #15

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.1290. Min Act: -0.0000

Data Index: 1327997 (The Pile)

Max Activating Token Index: 265

Text #16

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.2354. Min Act: -0.0000

Data Index: 1477375 (The Pile)

Max Activating Token Index: 381

Text #17

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.1580. Min Act: -0.0000

Data Index: 722163 (The Pile)

Max Activating Token Index: 315

Text #18

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.1574. Min Act: -0.0000

Data Index: 1729622 (The Pile)

Max Activating Token Index: 358

Text #19

Max Range: 1.5523. Min Range: -1.5523

Max Act: 1.1582. Min Act: -0.0000

Data Index: 1691448 (The Pile)

Max Activating Token Index: 494