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

Dataset: The Pile

Neuron 4390 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: 3.9737. Min Range: -3.9737

Max Act: 3.7715. Min Act: -0.0000

Data Index: 1589966 (The Pile)

Max Activating Token Index: 712

Text #1

Max Range: 3.9737. Min Range: -3.9737

Max Act: 3.7528. Min Act: -0.0000

Data Index: 1016147 (The Pile)

Max Activating Token Index: 387

Text #2

Max Range: 3.9737. Min Range: -3.9737

Max Act: 3.9737. Min Act: -0.0000

Data Index: 697417 (The Pile)

Max Activating Token Index: 68

Text #3

Max Range: 3.9737. Min Range: -3.9737

Max Act: 3.5379. Min Act: -0.0000

Data Index: 1319077 (The Pile)

Max Activating Token Index: 276

Text #4

Max Range: 3.9737. Min Range: -3.9737

Max Act: 3.4575. Min Act: -0.0000

Data Index: 923139 (The Pile)

Max Activating Token Index: 261

Text #5

Max Range: 3.9737. Min Range: -3.9737

Max Act: 3.3541. Min Act: -0.0000

Data Index: 676587 (The Pile)

Max Activating Token Index: 131

Text #6

Max Range: 3.9737. Min Range: -3.9737

Max Act: 3.3994. Min Act: -0.0000

Data Index: 1631290 (The Pile)

Max Activating Token Index: 210

Text #7

Max Range: 3.9737. Min Range: -3.9737

Max Act: 3.2066. Min Act: -0.0000

Data Index: 825518 (The Pile)

Max Activating Token Index: 380

Text #8

Max Range: 3.9737. Min Range: -3.9737

Max Act: 3.4409. Min Act: -0.0000

Data Index: 672981 (The Pile)

Max Activating Token Index: 41

Text #9

Max Range: 3.9737. Min Range: -3.9737

Max Act: 3.2482. Min Act: -0.0000

Data Index: 1341407 (The Pile)

Max Activating Token Index: 235

Text #10

Max Range: 3.9737. Min Range: -3.9737

Max Act: 3.2092. Min Act: -0.0000

Data Index: 671805 (The Pile)

Max Activating Token Index: 777

Text #11

Max Range: 3.9737. Min Range: -3.9737

Max Act: 2.9984. Min Act: 0.0000

Data Index: 1320465 (The Pile)

Max Activating Token Index: 639

Text #12

Max Range: 3.9737. Min Range: -3.9737

Max Act: 3.1405. Min Act: -0.0000

Data Index: 115648 (The Pile)

Max Activating Token Index: 154

Text #13

Max Range: 3.9737. Min Range: -3.9737

Max Act: 3.2727. Min Act: -0.0000

Data Index: 493416 (The Pile)

Max Activating Token Index: 229

Text #14

Max Range: 3.9737. Min Range: -3.9737

Max Act: 2.9800. Min Act: -0.0000

Data Index: 932349 (The Pile)

Max Activating Token Index: 82

Text #15

Max Range: 3.9737. Min Range: -3.9737

Max Act: 2.8258. Min Act: -0.0000

Data Index: 476146 (The Pile)

Max Activating Token Index: 962

Text #16

Max Range: 3.9737. Min Range: -3.9737

Max Act: 3.0658. Min Act: -0.0000

Data Index: 1228478 (The Pile)

Max Activating Token Index: 277

Text #17

Max Range: 3.9737. Min Range: -3.9737

Max Act: 2.7968. Min Act: -0.0000

Data Index: 1277622 (The Pile)

Max Activating Token Index: 719

Text #18

Max Range: 3.9737. Min Range: -3.9737

Max Act: 2.8181. Min Act: -0.0000

Data Index: 1112645 (The Pile)

Max Activating Token Index: 921

Text #19

Max Range: 3.9737. Min Range: -3.9737

Max Act: 2.5256. Min Act: -0.0000

Data Index: 376684 (The Pile)

Max Activating Token Index: 916