Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1932 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.9366. Min Act: -0.0000

Data Index: 1011606 (The Pile)

Max Activating Token Index: 187

Text #1

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.7602. Min Act: -0.0000

Data Index: 1797435 (The Pile)

Max Activating Token Index: 113

Text #2

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.8096. Min Act: -0.0000

Data Index: 1962781 (The Pile)

Max Activating Token Index: 96

Text #3

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.5908. Min Act: -0.0000

Data Index: 1610918 (The Pile)

Max Activating Token Index: 275

Text #4

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.7739. Min Act: -0.0000

Data Index: 1770353 (The Pile)

Max Activating Token Index: 754

Text #5

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.4180. Min Act: -0.0000

Data Index: 21083 (The Pile)

Max Activating Token Index: 274

Text #6

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.4235. Min Act: -0.0000

Data Index: 176568 (The Pile)

Max Activating Token Index: 168

Text #7

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.4939. Min Act: -0.0000

Data Index: 1668871 (The Pile)

Max Activating Token Index: 340

Text #8

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.3749. Min Act: -0.0000

Data Index: 718024 (The Pile)

Max Activating Token Index: 721

Text #9

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.4385. Min Act: -0.0000

Data Index: 286909 (The Pile)

Max Activating Token Index: 296

Text #10

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.3464. Min Act: -0.0000

Data Index: 1954749 (The Pile)

Max Activating Token Index: 202

Text #11

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.1421. Min Act: -0.0000

Data Index: 1887511 (The Pile)

Max Activating Token Index: 149

Text #12

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.3181. Min Act: -0.0000

Data Index: 377485 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.1629. Min Act: -0.0000

Data Index: 325035 (The Pile)

Max Activating Token Index: 270

Text #14

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.2655. Min Act: -0.0000

Data Index: 807329 (The Pile)

Max Activating Token Index: 645

Text #15

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.2199. Min Act: -0.0000

Data Index: 395622 (The Pile)

Max Activating Token Index: 346

Text #16

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.2542. Min Act: -0.0000

Data Index: 600580 (The Pile)

Max Activating Token Index: 917

Text #17

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.1811. Min Act: -0.0000

Data Index: 995755 (The Pile)

Max Activating Token Index: 207

Text #18

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.2044. Min Act: -0.0000

Data Index: 510137 (The Pile)

Max Activating Token Index: 808

Text #19

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.1905. Min Act: -0.0000

Data Index: 899684 (The Pile)

Max Activating Token Index: 72