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

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

Neuron 3655 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.3358. Min Act: -0.0001

Data Index: 21256 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2970. Min Act: -0.0001

Data Index: 244007 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2946. Min Act: -0.0001

Data Index: 738757 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2799. Min Act: -0.0001

Data Index: 885395 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2869. Min Act: -0.0001

Data Index: 636328 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2835. Min Act: -0.0001

Data Index: 1237829 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2737. Min Act: -0.0001

Data Index: 261188 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2888. Min Act: -0.0001

Data Index: 531013 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2967. Min Act: -0.0001

Data Index: 292260 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2715. Min Act: -0.0001

Data Index: 941912 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2654. Min Act: -0.0001

Data Index: 1118663 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2930. Min Act: -0.0001

Data Index: 143692 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2855. Min Act: -0.0001

Data Index: 631409 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2666. Min Act: -0.0001

Data Index: 36730 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2763. Min Act: -0.0001

Data Index: 1263964 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2661. Min Act: -0.0001

Data Index: 3957 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2720. Min Act: -0.0001

Data Index: 623288 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2618. Min Act: -0.0001

Data Index: 836240 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2628. Min Act: -0.0001

Data Index: 1280768 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2629. Min Act: -0.0001

Data Index: 1010623 (C4 (Web Text))

Max Activating Token Index: 657