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

Dataset: The Pile

Neuron 1258 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.3247. Min Act: -0.0000

Data Index: 352969 (The Pile)

Max Activating Token Index: 684

Text #1

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.8722. Min Act: -0.0000

Data Index: 231554 (The Pile)

Max Activating Token Index: 872

Text #2

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0038. Min Act: -0.0000

Data Index: 1363347 (The Pile)

Max Activating Token Index: 942

Text #3

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.8614. Min Act: -0.0000

Data Index: 1157099 (The Pile)

Max Activating Token Index: 803

Text #4

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.9994. Min Act: -0.0000

Data Index: 73875 (The Pile)

Max Activating Token Index: 307

Text #5

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.9888. Min Act: -0.0000

Data Index: 1309257 (The Pile)

Max Activating Token Index: 286

Text #6

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.1487. Min Act: -0.0000

Data Index: 962901 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.9361. Min Act: -0.0000

Data Index: 844891 (The Pile)

Max Activating Token Index: 326

Text #8

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.9101. Min Act: -0.0000

Data Index: 236798 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.9267. Min Act: -0.0000

Data Index: 1981949 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0194. Min Act: -0.0000

Data Index: 1851383 (The Pile)

Max Activating Token Index: 150

Text #11

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.1866. Min Act: -0.0000

Data Index: 483531 (The Pile)

Max Activating Token Index: 705

Text #12

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.7428. Min Act: -0.0000

Data Index: 873200 (The Pile)

Max Activating Token Index: 974

Text #13

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.9329. Min Act: -0.0000

Data Index: 371404 (The Pile)

Max Activating Token Index: 271

Text #14

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.9409. Min Act: -0.0000

Data Index: 1886126 (The Pile)

Max Activating Token Index: 125

Text #15

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.9108. Min Act: -0.0000

Data Index: 1563825 (The Pile)

Max Activating Token Index: 29

Text #16

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.8866. Min Act: -0.0000

Data Index: 1367474 (The Pile)

Max Activating Token Index: 855

Text #17

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.8950. Min Act: -0.0000

Data Index: 861499 (The Pile)

Max Activating Token Index: 266

Text #18

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.8789. Min Act: -0.0000

Data Index: 1577135 (The Pile)

Max Activating Token Index: 269

Text #19

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0129. Min Act: -0.0000

Data Index: 747674 (The Pile)

Max Activating Token Index: 458