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

Dataset: The Pile

Neuron 2289 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: 0.3861. Min Range: -0.3861

Max Act: 0.3861. Min Act: -0.0000

Data Index: 529665 (The Pile)

Max Activating Token Index: 115

Text #1

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3681. Min Act: -0.0000

Data Index: 1559557 (The Pile)

Max Activating Token Index: 394

Text #2

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1937364 (The Pile)

Max Activating Token Index: 463

Text #3

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3378. Min Act: -0.0000

Data Index: 560638 (The Pile)

Max Activating Token Index: 366

Text #4

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3343. Min Act: -0.0000

Data Index: 1815688 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3343. Min Act: -0.0000

Data Index: 837507 (The Pile)

Max Activating Token Index: 915

Text #6

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3222. Min Act: -0.0000

Data Index: 755073 (The Pile)

Max Activating Token Index: 382

Text #7

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3303. Min Act: -0.0000

Data Index: 792486 (The Pile)

Max Activating Token Index: 296

Text #8

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1880357 (The Pile)

Max Activating Token Index: 761

Text #9

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3341. Min Act: -0.0000

Data Index: 1761702 (The Pile)

Max Activating Token Index: 85

Text #10

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3236. Min Act: -0.0000

Data Index: 721939 (The Pile)

Max Activating Token Index: 241

Text #11

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3224. Min Act: -0.0000

Data Index: 1987158 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3232. Min Act: -0.0000

Data Index: 229692 (The Pile)

Max Activating Token Index: 471

Text #13

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3222. Min Act: -0.0000

Data Index: 1042049 (The Pile)

Max Activating Token Index: 213

Text #14

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3219. Min Act: -0.0000

Data Index: 731465 (The Pile)

Max Activating Token Index: 246

Text #15

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3215. Min Act: -0.0000

Data Index: 1864850 (The Pile)

Max Activating Token Index: 311

Text #16

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3120. Min Act: -0.0000

Data Index: 729951 (The Pile)

Max Activating Token Index: 167

Text #17

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3328. Min Act: -0.0000

Data Index: 1783175 (The Pile)

Max Activating Token Index: 473

Text #18

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3308. Min Act: -0.0000

Data Index: 1501925 (The Pile)

Max Activating Token Index: 155

Text #19

Max Range: 0.3861. Min Range: -0.3861

Max Act: 0.3170. Min Act: -0.0000

Data Index: 1969180 (The Pile)

Max Activating Token Index: 112