Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3001 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.5790. Min Act: -0.0000

Data Index: 1242159 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3449. Min Act: -0.0000

Data Index: 198240 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3459. Min Act: -0.0000

Data Index: 440553 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3484. Min Act: -0.0000

Data Index: 180174 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3373. Min Act: -0.0000

Data Index: 398256 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3420. Min Act: -0.0000

Data Index: 771131 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3490. Min Act: -0.0000

Data Index: 1007082 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3217. Min Act: -0.0000

Data Index: 6835 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.2910. Min Act: -0.0000

Data Index: 684811 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1086330 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.2859. Min Act: -0.0001

Data Index: 721885 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3041. Min Act: -0.0000

Data Index: 596596 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.2870. Min Act: -0.0000

Data Index: 1151812 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.2965. Min Act: -0.0001

Data Index: 1316870 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.2938. Min Act: -0.0001

Data Index: 564313 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.2903. Min Act: -0.0000

Data Index: 947193 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1246914 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1242915 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.2929. Min Act: -0.0000

Data Index: 768152 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.5790. Min Range: -0.5790

Max Act: 0.3000. Min Act: -0.0000

Data Index: 335148 (C4 (Web Text))

Max Activating Token Index: 957