Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4878 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.8728. Min Act: -0.0000

Data Index: 716974 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7568. Min Act: -0.0000

Data Index: 613685 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7292. Min Act: -0.0000

Data Index: 97086 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6993. Min Act: -0.0000

Data Index: 743941 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6772. Min Act: -0.0000

Data Index: 132957 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6849. Min Act: -0.0000

Data Index: 601009 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6816. Min Act: -0.0000

Data Index: 3548 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7007. Min Act: -0.0000

Data Index: 1306610 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6777. Min Act: -0.0000

Data Index: 102187 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6272. Min Act: -0.0000

Data Index: 624236 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1211851 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6578. Min Act: -0.0000

Data Index: 995498 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1095694 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6570. Min Act: -0.0000

Data Index: 173649 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6297. Min Act: -0.0000

Data Index: 885443 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6489. Min Act: -0.0000

Data Index: 736758 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6150. Min Act: -0.0000

Data Index: 88799 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6342. Min Act: -0.0000

Data Index: 1084977 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6503. Min Act: -0.0000

Data Index: 942359 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6317. Min Act: -0.0000

Data Index: 149652 (C4 (Web Text))

Max Activating Token Index: 514