Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1457 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1046708 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3675. Min Act: -0.0000

Data Index: 577161 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2792. Min Act: -0.0000

Data Index: 1318312 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3160. Min Act: -0.0000

Data Index: 993465 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3077. Min Act: -0.0000

Data Index: 306856 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2895. Min Act: -0.0000

Data Index: 396316 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1305020 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3117. Min Act: -0.0000

Data Index: 1123125 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2753. Min Act: -0.0000

Data Index: 455144 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2851. Min Act: -0.0000

Data Index: 160913 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2642. Min Act: -0.0000

Data Index: 714107 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1143634 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2555. Min Act: -0.0000

Data Index: 429910 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1127668 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2601. Min Act: -0.0000

Data Index: 6508 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2515. Min Act: -0.0000

Data Index: 764452 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2185. Min Act: -0.0000

Data Index: 887016 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2329. Min Act: -0.0000

Data Index: 409182 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2300. Min Act: -0.0000

Data Index: 1137080 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2201. Min Act: -0.0000

Data Index: 1245796 (C4 (Web Text))

Max Activating Token Index: 404