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

Dataset: The Pile

Neuron 2618 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.3848. Min Act: -0.0000

Data Index: 1293324 (The Pile)

Max Activating Token Index: 280

Text #1

Max Range: 1.3848. Min Range: -1.3848

Max Act: 1.0216. Min Act: -0.0000

Data Index: 1215111 (The Pile)

Max Activating Token Index: 339

Text #2

Max Range: 1.3848. Min Range: -1.3848

Max Act: 0.9598. Min Act: -0.0000

Data Index: 1746880 (The Pile)

Max Activating Token Index: 341

Text #3

Max Range: 1.3848. Min Range: -1.3848

Max Act: 0.9352. Min Act: -0.0000

Data Index: 358243 (The Pile)

Max Activating Token Index: 533

Text #4

Max Range: 1.3848. Min Range: -1.3848

Max Act: 0.8308. Min Act: -0.0000

Data Index: 1939271 (The Pile)

Max Activating Token Index: 998

Text #5

Max Range: 1.3848. Min Range: -1.3848

Max Act: 0.8255. Min Act: -0.0000

Data Index: 43700 (The Pile)

Max Activating Token Index: 593

Text #6

Max Range: 1.3848. Min Range: -1.3848

Max Act: 0.8956. Min Act: -0.0000

Data Index: 316455 (The Pile)

Max Activating Token Index: 99

Text #7

Max Range: 1.3848. Min Range: -1.3848

Max Act: 0.8268. Min Act: -0.0000

Data Index: 279030 (The Pile)

Max Activating Token Index: 809

Text #8

Max Range: 1.3848. Min Range: -1.3848

Max Act: 0.8468. Min Act: -0.0000

Data Index: 1258510 (The Pile)

Max Activating Token Index: 382

Text #9

Max Range: 1.3848. Min Range: -1.3848

Max Act: 0.7905. Min Act: -0.0000

Data Index: 942103 (The Pile)

Max Activating Token Index: 747

Text #10

Max Range: 1.3848. Min Range: -1.3848

Max Act: 0.7572. Min Act: -0.0000

Data Index: 1157368 (The Pile)

Max Activating Token Index: 998

Text #11

Max Range: 1.3848. Min Range: -1.3848

Max Act: 0.7805. Min Act: -0.0000

Data Index: 592742 (The Pile)

Max Activating Token Index: 432

Text #12

Max Range: 1.3848. Min Range: -1.3848

Max Act: 0.7758. Min Act: -0.0000

Data Index: 376112 (The Pile)

Max Activating Token Index: 295

Text #13

Max Range: 1.3848. Min Range: -1.3848

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1521953 (The Pile)

Max Activating Token Index: 805

Text #14

Max Range: 1.3848. Min Range: -1.3848

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1441006 (The Pile)

Max Activating Token Index: 157

Text #15

Max Range: 1.3848. Min Range: -1.3848

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1085151 (The Pile)

Max Activating Token Index: 162

Text #16

Max Range: 1.3848. Min Range: -1.3848

Max Act: 0.7033. Min Act: -0.0000

Data Index: 488136 (The Pile)

Max Activating Token Index: 112

Text #17

Max Range: 1.3848. Min Range: -1.3848

Max Act: 0.6520. Min Act: -0.0000

Data Index: 987506 (The Pile)

Max Activating Token Index: 832

Text #18

Max Range: 1.3848. Min Range: -1.3848

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1270212 (The Pile)

Max Activating Token Index: 42

Text #19

Max Range: 1.3848. Min Range: -1.3848

Max Act: 0.7224. Min Act: -0.0000

Data Index: 1606897 (The Pile)

Max Activating Token Index: 942