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

Dataset: The Pile

Neuron 2794 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: 1.6450. Min Range: -1.6450

Max Act: 1.6450. Min Act: -0.0000

Data Index: 987620 (The Pile)

Max Activating Token Index: 241

Text #1

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.5314. Min Act: -0.0000

Data Index: 1618691 (The Pile)

Max Activating Token Index: 984

Text #2

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.4337. Min Act: -0.0000

Data Index: 1998059 (The Pile)

Max Activating Token Index: 547

Text #3

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.3052. Min Act: -0.0000

Data Index: 1862697 (The Pile)

Max Activating Token Index: 348

Text #4

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.3960. Min Act: -0.0000

Data Index: 1449631 (The Pile)

Max Activating Token Index: 782

Text #5

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.1848. Min Act: -0.0000

Data Index: 827217 (The Pile)

Max Activating Token Index: 6

Text #6

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.1532. Min Act: -0.0000

Data Index: 1744226 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.2134. Min Act: -0.0000

Data Index: 933166 (The Pile)

Max Activating Token Index: 226

Text #8

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.2127. Min Act: -0.0000

Data Index: 1400635 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.1286. Min Act: -0.0000

Data Index: 987641 (The Pile)

Max Activating Token Index: 290

Text #10

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.1216. Min Act: -0.0000

Data Index: 1269998 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.1258. Min Act: -0.0000

Data Index: 1394119 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.0495. Min Act: -0.0000

Data Index: 1439342 (The Pile)

Max Activating Token Index: 160

Text #13

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.0827. Min Act: -0.0000

Data Index: 162874 (The Pile)

Max Activating Token Index: 816

Text #14

Max Range: 1.6450. Min Range: -1.6450

Max Act: 0.9759. Min Act: -0.0000

Data Index: 57508 (The Pile)

Max Activating Token Index: 592

Text #15

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.0188. Min Act: -0.0000

Data Index: 1625777 (The Pile)

Max Activating Token Index: 826

Text #16

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.2075. Min Act: -0.0000

Data Index: 719986 (The Pile)

Max Activating Token Index: 1012

Text #17

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.0605. Min Act: -0.0000

Data Index: 1761335 (The Pile)

Max Activating Token Index: 169

Text #18

Max Range: 1.6450. Min Range: -1.6450

Max Act: 0.9893. Min Act: -0.0000

Data Index: 849933 (The Pile)

Max Activating Token Index: 831

Text #19

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.0410. Min Act: -0.0000

Data Index: 1312467 (The Pile)

Max Activating Token Index: 87