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

Dataset: The Pile

Neuron 4297 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: 0.1674. Min Range: -0.1674

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1719024 (The Pile)

Max Activating Token Index: 241

Text #1

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1324. Min Act: -0.0000

Data Index: 728129 (The Pile)

Max Activating Token Index: 237

Text #2

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1202. Min Act: -0.0000

Data Index: 383569 (The Pile)

Max Activating Token Index: 122

Text #3

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1260. Min Act: -0.0000

Data Index: 1863102 (The Pile)

Max Activating Token Index: 512

Text #4

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1692926 (The Pile)

Max Activating Token Index: 202

Text #5

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1243. Min Act: -0.0000

Data Index: 378887 (The Pile)

Max Activating Token Index: 773

Text #6

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1145. Min Act: -0.0000

Data Index: 31211 (The Pile)

Max Activating Token Index: 12

Text #7

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1137. Min Act: -0.0000

Data Index: 774740 (The Pile)

Max Activating Token Index: 604

Text #8

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1158. Min Act: -0.0000

Data Index: 159964 (The Pile)

Max Activating Token Index: 1020

Text #9

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1203. Min Act: -0.0000

Data Index: 1954116 (The Pile)

Max Activating Token Index: 789

Text #10

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1267244 (The Pile)

Max Activating Token Index: 406

Text #11

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1071278 (The Pile)

Max Activating Token Index: 521

Text #12

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1494713 (The Pile)

Max Activating Token Index: 694

Text #13

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1001. Min Act: -0.0000

Data Index: 774154 (The Pile)

Max Activating Token Index: 924

Text #14

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1117. Min Act: -0.0000

Data Index: 1618383 (The Pile)

Max Activating Token Index: 466

Text #15

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1110. Min Act: -0.0000

Data Index: 286773 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1774576 (The Pile)

Max Activating Token Index: 962

Text #17

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.0928. Min Act: -0.0000

Data Index: 387345 (The Pile)

Max Activating Token Index: 929

Text #18

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1024. Min Act: -0.0000

Data Index: 61767 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1025. Min Act: -0.0000

Data Index: 882978 (The Pile)

Max Activating Token Index: 473