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

Dataset: The Pile

Neuron 204 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: 0.4092. Min Range: -0.4092

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1457079 (The Pile)

Max Activating Token Index: 968

Text #1

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1002860 (The Pile)

Max Activating Token Index: 190

Text #2

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2798. Min Act: -0.0000

Data Index: 1974593 (The Pile)

Max Activating Token Index: 50

Text #3

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1051880 (The Pile)

Max Activating Token Index: 646

Text #4

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2502. Min Act: -0.0000

Data Index: 1686815 (The Pile)

Max Activating Token Index: 903

Text #5

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2574. Min Act: -0.0000

Data Index: 1498173 (The Pile)

Max Activating Token Index: 41

Text #6

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1139709 (The Pile)

Max Activating Token Index: 803

Text #7

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2545. Min Act: -0.0000

Data Index: 164699 (The Pile)

Max Activating Token Index: 48

Text #8

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2490. Min Act: -0.0000

Data Index: 175480 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2336. Min Act: -0.0000

Data Index: 1773838 (The Pile)

Max Activating Token Index: 299

Text #10

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1798232 (The Pile)

Max Activating Token Index: 747

Text #11

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2403. Min Act: -0.0000

Data Index: 372625 (The Pile)

Max Activating Token Index: 985

Text #12

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2381. Min Act: -0.0000

Data Index: 751141 (The Pile)

Max Activating Token Index: 775

Text #13

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2344. Min Act: -0.0000

Data Index: 76859 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2314. Min Act: -0.0000

Data Index: 666964 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1127575 (The Pile)

Max Activating Token Index: 170

Text #16

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2332. Min Act: -0.0000

Data Index: 42312 (The Pile)

Max Activating Token Index: 235

Text #17

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2188. Min Act: -0.0000

Data Index: 964984 (The Pile)

Max Activating Token Index: 905

Text #18

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1926907 (The Pile)

Max Activating Token Index: 196

Text #19

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.2241. Min Act: -0.0000

Data Index: 496090 (The Pile)

Max Activating Token Index: 174