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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1069 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.4113. Min Act: -0.0000

Data Index: 519461 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.3465. Min Act: -0.0000

Data Index: 354488 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.3043. Min Act: -0.0000

Data Index: 716289 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.2142. Min Act: -0.0000

Data Index: 349627 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.1158. Min Act: -0.0000

Data Index: 391257 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.1001. Min Act: -0.0000

Data Index: 1274707 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.1180. Min Act: -0.0000

Data Index: 881974 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0679. Min Act: -0.0000

Data Index: 703663 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.1712. Min Act: -0.0000

Data Index: 1343937 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0962. Min Act: -0.0000

Data Index: 1264030 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.1365. Min Act: -0.0000

Data Index: 281089 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0819. Min Act: -0.0000

Data Index: 877188 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0858. Min Act: -0.0000

Data Index: 633840 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0488. Min Act: -0.0000

Data Index: 70188 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0425. Min Act: -0.0000

Data Index: 117323 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0931. Min Act: -0.0000

Data Index: 936737 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0539. Min Act: -0.0000

Data Index: 395399 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0535. Min Act: -0.0000

Data Index: 488421 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 1.4113. Min Range: -1.4113

Max Act: 0.9449. Min Act: -0.0000

Data Index: 437883 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 1.4113. Min Range: -1.4113

Max Act: 1.0274. Min Act: -0.0000

Data Index: 1068085 (C4 (Web Text))

Max Activating Token Index: 731