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

Dataset: The Pile

Neuron 1302 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0367. Min Act: -0.0000

Data Index: 556424 (The Pile)

Max Activating Token Index: 699

Text #1

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0333. Min Act: -0.0000

Data Index: 744984 (The Pile)

Max Activating Token Index: 313

Text #2

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0310. Min Act: -0.0000

Data Index: 758002 (The Pile)

Max Activating Token Index: 170

Text #3

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0244. Min Act: -0.0000

Data Index: 916351 (The Pile)

Max Activating Token Index: 684

Text #4

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0231. Min Act: -0.0000

Data Index: 742260 (The Pile)

Max Activating Token Index: 436

Text #5

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0219. Min Act: -0.0000

Data Index: 1816740 (The Pile)

Max Activating Token Index: 691

Text #6

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0204. Min Act: -0.0000

Data Index: 1389163 (The Pile)

Max Activating Token Index: 154

Text #7

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0217. Min Act: -0.0000

Data Index: 1729831 (The Pile)

Max Activating Token Index: 177

Text #8

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0198. Min Act: -0.0000

Data Index: 337808 (The Pile)

Max Activating Token Index: 589

Text #9

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0202. Min Act: -0.0000

Data Index: 257656 (The Pile)

Max Activating Token Index: 245

Text #10

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0194. Min Act: -0.0000

Data Index: 403482 (The Pile)

Max Activating Token Index: 538

Text #11

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0195. Min Act: -0.0000

Data Index: 1336829 (The Pile)

Max Activating Token Index: 128

Text #12

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0200. Min Act: -0.0000

Data Index: 469406 (The Pile)

Max Activating Token Index: 697

Text #13

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0199. Min Act: -0.0000

Data Index: 749411 (The Pile)

Max Activating Token Index: 239

Text #14

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0197. Min Act: -0.0000

Data Index: 476691 (The Pile)

Max Activating Token Index: 252

Text #15

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0194. Min Act: -0.0000

Data Index: 419075 (The Pile)

Max Activating Token Index: 23

Text #16

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0185. Min Act: -0.0000

Data Index: 1317694 (The Pile)

Max Activating Token Index: 93

Text #17

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0189. Min Act: -0.0000

Data Index: 1200044 (The Pile)

Max Activating Token Index: 166

Text #18

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0175. Min Act: -0.0000

Data Index: 1371276 (The Pile)

Max Activating Token Index: 863

Text #19

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0174. Min Act: -0.0000

Data Index: 846179 (The Pile)

Max Activating Token Index: 52