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

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

Neuron 1033 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.7630. Min Act: -0.0001

Data Index: 1236404 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.7547. Min Act: -0.0001

Data Index: 892270 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.7607. Min Act: -0.0001

Data Index: 1330660 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6750. Min Act: -0.0002

Data Index: 420301 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6777. Min Act: -0.0002

Data Index: 1254609 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5790. Min Act: -0.0002

Data Index: 78772 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6649. Min Act: -0.0001

Data Index: 4001 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6934. Min Act: -0.0002

Data Index: 730024 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5829. Min Act: -0.0002

Data Index: 1233300 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5857. Min Act: -0.0001

Data Index: 403116 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5749. Min Act: -0.0002

Data Index: 1211781 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6127. Min Act: -0.0001

Data Index: 826549 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6686. Min Act: -0.0001

Data Index: 825243 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6573. Min Act: -0.0002

Data Index: 547965 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6296. Min Act: -0.0001

Data Index: 1164224 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6002. Min Act: -0.0001

Data Index: 1075771 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5748. Min Act: -0.0002

Data Index: 1210886 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5851. Min Act: -0.0001

Data Index: 332646 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6146. Min Act: -0.0001

Data Index: 331812 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5995. Min Act: -0.0001

Data Index: 1067635 (C4 (Web Text))

Max Activating Token Index: 139