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

Dataset: The Pile

Neuron 2155 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: 3.8515. Min Range: -3.8515

Max Act: 3.8515. Min Act: -0.0000

Data Index: 1529626 (The Pile)

Max Activating Token Index: 721

Text #1

Max Range: 3.8515. Min Range: -3.8515

Max Act: 3.3142. Min Act: -0.0000

Data Index: 795857 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 3.8515. Min Range: -3.8515

Max Act: 2.9795. Min Act: -0.0000

Data Index: 1026148 (The Pile)

Max Activating Token Index: 344

Text #3

Max Range: 3.8515. Min Range: -3.8515

Max Act: 3.0903. Min Act: -0.0000

Data Index: 755761 (The Pile)

Max Activating Token Index: 40

Text #4

Max Range: 3.8515. Min Range: -3.8515

Max Act: 3.4621. Min Act: -0.0000

Data Index: 1456761 (The Pile)

Max Activating Token Index: 799

Text #5

Max Range: 3.8515. Min Range: -3.8515

Max Act: 2.9656. Min Act: -0.0000

Data Index: 928570 (The Pile)

Max Activating Token Index: 153

Text #6

Max Range: 3.8515. Min Range: -3.8515

Max Act: 2.8653. Min Act: -0.0000

Data Index: 1329105 (The Pile)

Max Activating Token Index: 93

Text #7

Max Range: 3.8515. Min Range: -3.8515

Max Act: 2.8796. Min Act: -0.0000

Data Index: 1681142 (The Pile)

Max Activating Token Index: 401

Text #8

Max Range: 3.8515. Min Range: -3.8515

Max Act: 2.8181. Min Act: -0.0000

Data Index: 1466986 (The Pile)

Max Activating Token Index: 95

Text #9

Max Range: 3.8515. Min Range: -3.8515

Max Act: 3.0634. Min Act: -0.0000

Data Index: 1099563 (The Pile)

Max Activating Token Index: 413

Text #10

Max Range: 3.8515. Min Range: -3.8515

Max Act: 3.0165. Min Act: -0.0000

Data Index: 436991 (The Pile)

Max Activating Token Index: 556

Text #11

Max Range: 3.8515. Min Range: -3.8515

Max Act: 2.6759. Min Act: -0.0000

Data Index: 1215016 (The Pile)

Max Activating Token Index: 751

Text #12

Max Range: 3.8515. Min Range: -3.8515

Max Act: 2.4780. Min Act: -0.0000

Data Index: 985078 (The Pile)

Max Activating Token Index: 419

Text #13

Max Range: 3.8515. Min Range: -3.8515

Max Act: 2.4281. Min Act: -0.0000

Data Index: 1288691 (The Pile)

Max Activating Token Index: 755

Text #14

Max Range: 3.8515. Min Range: -3.8515

Max Act: 2.4557. Min Act: -0.0000

Data Index: 1406500 (The Pile)

Max Activating Token Index: 128

Text #15

Max Range: 3.8515. Min Range: -3.8515

Max Act: 2.2798. Min Act: -0.0000

Data Index: 1601695 (The Pile)

Max Activating Token Index: 856

Text #16

Max Range: 3.8515. Min Range: -3.8515

Max Act: 2.4397. Min Act: -0.0000

Data Index: 550517 (The Pile)

Max Activating Token Index: 675

Text #17

Max Range: 3.8515. Min Range: -3.8515

Max Act: 2.1257. Min Act: -0.0000

Data Index: 1572056 (The Pile)

Max Activating Token Index: 1011

Text #18

Max Range: 3.8515. Min Range: -3.8515

Max Act: 2.2609. Min Act: -0.0000

Data Index: 72359 (The Pile)

Max Activating Token Index: 158

Text #19

Max Range: 3.8515. Min Range: -3.8515

Max Act: 2.3736. Min Act: -0.0000

Data Index: 882204 (The Pile)

Max Activating Token Index: 492