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

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

Neuron 1589 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.9893. Min Act: -0.0001

Data Index: 1274750 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8784. Min Act: -0.0001

Data Index: 1342866 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.9186. Min Act: -0.0001

Data Index: 1350956 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8046. Min Act: -0.0001

Data Index: 218620 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.7568. Min Act: -0.0001

Data Index: 171611 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.7292. Min Act: -0.0001

Data Index: 1355108 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.7103. Min Act: -0.0001

Data Index: 36903 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.6951. Min Act: -0.0001

Data Index: 1193991 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.6613. Min Act: -0.0001

Data Index: 603561 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.6755. Min Act: -0.0001

Data Index: 204218 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.6924. Min Act: -0.0001

Data Index: 617401 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.6723. Min Act: -0.0001

Data Index: 928466 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.6661. Min Act: -0.0001

Data Index: 213498 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.6915. Min Act: -0.0001

Data Index: 751929 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.6683. Min Act: -0.0001

Data Index: 223352 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.6428. Min Act: -0.0001

Data Index: 1054631 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.6620. Min Act: -0.0001

Data Index: 284477 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.6800. Min Act: -0.0001

Data Index: 955907 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.6389. Min Act: -0.0001

Data Index: 768432 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.6385. Min Act: -0.0001

Data Index: 249783 (C4 (Web Text))

Max Activating Token Index: 138