Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 980 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.3788. Min Act: -0.0001

Data Index: 289838 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5134. Min Act: -0.0001

Data Index: 1257228 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.6093. Min Act: -0.0001

Data Index: 168148 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.4124. Min Act: -0.0001

Data Index: 958443 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.4823. Min Act: -0.0001

Data Index: 1086210 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5426. Min Act: -0.0001

Data Index: 139385 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.4389. Min Act: -0.0001

Data Index: 1351395 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.3926. Min Act: -0.0001

Data Index: 998147 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.4027. Min Act: -0.0001

Data Index: 1329434 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.3714. Min Act: -0.0001

Data Index: 289776 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.2930. Min Act: -0.0001

Data Index: 131370 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.4530. Min Act: -0.0001

Data Index: 1152251 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.3640. Min Act: -0.0001

Data Index: 433853 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.1528. Min Act: -0.0001

Data Index: 848766 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.2676. Min Act: -0.0001

Data Index: 560240 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.4588. Min Act: -0.0001

Data Index: 1012310 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.4576. Min Act: -0.0001

Data Index: 300514 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.3170. Min Act: -0.0001

Data Index: 417368 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.2769. Min Act: -0.0001

Data Index: 88678 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.3732. Min Act: -0.0001

Data Index: 728023 (C4 (Web Text))

Max Activating Token Index: 875