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

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

Neuron 4043 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.9961. Min Act: -0.0000

Data Index: 787720 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 1.0242. Min Range: -1.0242

Max Act: 1.0242. Min Act: -0.0000

Data Index: 1092852 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.8861. Min Act: -0.0000

Data Index: 1072964 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.8620. Min Act: -0.0000

Data Index: 1049617 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.8562. Min Act: -0.0000

Data Index: 567321 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.7590. Min Act: -0.0000

Data Index: 889546 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.7771. Min Act: -0.0000

Data Index: 906055 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1312403 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.7461. Min Act: -0.0000

Data Index: 1183311 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.7400. Min Act: -0.0000

Data Index: 116217 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.7140. Min Act: -0.0000

Data Index: 881515 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.7201. Min Act: -0.0000

Data Index: 24122 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.7192. Min Act: -0.0000

Data Index: 1310307 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.7172. Min Act: -0.0000

Data Index: 31827 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1199999 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.7055. Min Act: -0.0000

Data Index: 1067499 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.6839. Min Act: -0.0000

Data Index: 1006445 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.6293. Min Act: -0.0000

Data Index: 767793 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.6350. Min Act: -0.0000

Data Index: 315621 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.6764. Min Act: -0.0000

Data Index: 382948 (C4 (Web Text))

Max Activating Token Index: 646