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

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

Neuron 807 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: 0.9782. Min Range: -0.9782

Max Act: 0.9782. Min Act: -0.0000

Data Index: 200038 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7826. Min Act: -0.0000

Data Index: 619351 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7478. Min Act: -0.0000

Data Index: 489888 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6101. Min Act: -0.0000

Data Index: 968888 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6832. Min Act: -0.0000

Data Index: 856802 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6818. Min Act: -0.0000

Data Index: 13565 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6969. Min Act: -0.0000

Data Index: 141956 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6531. Min Act: -0.0000

Data Index: 957651 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6518. Min Act: -0.0000

Data Index: 300381 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6497. Min Act: -0.0000

Data Index: 1119294 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6185. Min Act: -0.0000

Data Index: 419820 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6495. Min Act: -0.0000

Data Index: 1265358 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6107. Min Act: -0.0000

Data Index: 837632 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.5950. Min Act: -0.0000

Data Index: 918818 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1281761 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.5891. Min Act: -0.0000

Data Index: 305810 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.5317. Min Act: -0.0000

Data Index: 1283791 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1122148 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.5576. Min Act: -0.0000

Data Index: 810901 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1017536 (C4 (Web Text))

Max Activating Token Index: 690