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

Dataset: The Pile

Neuron 2090 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: 0.9197. Min Range: -0.9197

Max Act: 0.8507. Min Act: -0.0000

Data Index: 878067 (The Pile)

Max Activating Token Index: 928

Text #1

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.9197. Min Act: -0.0000

Data Index: 1151617 (The Pile)

Max Activating Token Index: 682

Text #2

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.8279. Min Act: -0.0000

Data Index: 918980 (The Pile)

Max Activating Token Index: 470

Text #3

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7822. Min Act: -0.0000

Data Index: 1399 (The Pile)

Max Activating Token Index: 609

Text #4

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7301. Min Act: -0.0000

Data Index: 475091 (The Pile)

Max Activating Token Index: 919

Text #5

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1994101 (The Pile)

Max Activating Token Index: 620

Text #6

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7087. Min Act: -0.0000

Data Index: 330036 (The Pile)

Max Activating Token Index: 362

Text #7

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7555. Min Act: -0.0000

Data Index: 1497627 (The Pile)

Max Activating Token Index: 558

Text #8

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1343946 (The Pile)

Max Activating Token Index: 763

Text #9

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7152. Min Act: -0.0000

Data Index: 1224589 (The Pile)

Max Activating Token Index: 739

Text #10

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7161. Min Act: -0.0000

Data Index: 604585 (The Pile)

Max Activating Token Index: 965

Text #11

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.6596. Min Act: -0.0000

Data Index: 23158 (The Pile)

Max Activating Token Index: 286

Text #12

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7027. Min Act: -0.0000

Data Index: 734280 (The Pile)

Max Activating Token Index: 266

Text #13

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7949. Min Act: -0.0000

Data Index: 333771 (The Pile)

Max Activating Token Index: 831

Text #14

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1499490 (The Pile)

Max Activating Token Index: 744

Text #15

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7347. Min Act: -0.0000

Data Index: 1276974 (The Pile)

Max Activating Token Index: 226

Text #16

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.6771. Min Act: -0.0000

Data Index: 299308 (The Pile)

Max Activating Token Index: 709

Text #17

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1376748 (The Pile)

Max Activating Token Index: 512

Text #18

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.6325. Min Act: -0.0000

Data Index: 289837 (The Pile)

Max Activating Token Index: 258

Text #19

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1839306 (The Pile)

Max Activating Token Index: 155