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

Dataset: The Pile

Neuron 4883 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: 0.1726. Min Range: -0.1726

Max Act: 0.1500. Min Act: -0.0000

Data Index: 1354477 (The Pile)

Max Activating Token Index: 597

Text #1

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1726. Min Act: -0.0000

Data Index: 845105 (The Pile)

Max Activating Token Index: 930

Text #2

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1388. Min Act: -0.0000

Data Index: 1195634 (The Pile)

Max Activating Token Index: 593

Text #3

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1379. Min Act: -0.0000

Data Index: 318704 (The Pile)

Max Activating Token Index: 830

Text #4

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1453. Min Act: -0.0000

Data Index: 1635508 (The Pile)

Max Activating Token Index: 348

Text #5

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1348. Min Act: -0.0000

Data Index: 1448157 (The Pile)

Max Activating Token Index: 684

Text #6

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1168. Min Act: -0.0000

Data Index: 987266 (The Pile)

Max Activating Token Index: 732

Text #7

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1991843 (The Pile)

Max Activating Token Index: 471

Text #8

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1249. Min Act: -0.0000

Data Index: 356695 (The Pile)

Max Activating Token Index: 1020

Text #9

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1118904 (The Pile)

Max Activating Token Index: 817

Text #10

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1098205 (The Pile)

Max Activating Token Index: 442

Text #11

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1806712 (The Pile)

Max Activating Token Index: 228

Text #12

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1123. Min Act: -0.0000

Data Index: 1887641 (The Pile)

Max Activating Token Index: 589

Text #13

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1083. Min Act: -0.0000

Data Index: 163471 (The Pile)

Max Activating Token Index: 660

Text #14

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1092. Min Act: -0.0000

Data Index: 1552137 (The Pile)

Max Activating Token Index: 446

Text #15

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1705142 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1096. Min Act: -0.0000

Data Index: 1180469 (The Pile)

Max Activating Token Index: 356

Text #17

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1050. Min Act: -0.0000

Data Index: 370077 (The Pile)

Max Activating Token Index: 669

Text #18

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1241. Min Act: -0.0000

Data Index: 375676 (The Pile)

Max Activating Token Index: 852

Text #19

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1092. Min Act: -0.0000

Data Index: 493744 (The Pile)

Max Activating Token Index: 544