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

Dataset: The Pile

Neuron 2530 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1579662 (The Pile)

Max Activating Token Index: 118

Text #1

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1967818 (The Pile)

Max Activating Token Index: 61

Text #2

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2819. Min Act: -0.0000

Data Index: 777798 (The Pile)

Max Activating Token Index: 102

Text #3

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2792. Min Act: -0.0000

Data Index: 1659230 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2794. Min Act: -0.0000

Data Index: 1569626 (The Pile)

Max Activating Token Index: 834

Text #5

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2672. Min Act: -0.0000

Data Index: 1278059 (The Pile)

Max Activating Token Index: 276

Text #6

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1239846 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1665587 (The Pile)

Max Activating Token Index: 838

Text #8

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2392. Min Act: -0.0000

Data Index: 1124389 (The Pile)

Max Activating Token Index: 527

Text #9

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2439. Min Act: -0.0000

Data Index: 406234 (The Pile)

Max Activating Token Index: 672

Text #10

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2348. Min Act: -0.0000

Data Index: 1798155 (The Pile)

Max Activating Token Index: 358

Text #11

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2083. Min Act: -0.0000

Data Index: 1964487 (The Pile)

Max Activating Token Index: 717

Text #12

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2262. Min Act: -0.0000

Data Index: 587198 (The Pile)

Max Activating Token Index: 775

Text #13

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2025. Min Act: -0.0000

Data Index: 414988 (The Pile)

Max Activating Token Index: 725

Text #14

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2239. Min Act: -0.0000

Data Index: 545892 (The Pile)

Max Activating Token Index: 449

Text #15

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1275206 (The Pile)

Max Activating Token Index: 272

Text #16

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2138. Min Act: -0.0000

Data Index: 334206 (The Pile)

Max Activating Token Index: 597

Text #17

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2242. Min Act: -0.0000

Data Index: 40498 (The Pile)

Max Activating Token Index: 366

Text #18

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1189139 (The Pile)

Max Activating Token Index: 383

Text #19

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2141. Min Act: -0.0000

Data Index: 816881 (The Pile)

Max Activating Token Index: 483