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

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

Neuron 2587 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.3210. Min Act: -0.0000

Data Index: 407979 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2869. Min Act: -0.0001

Data Index: 772450 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.3023. Min Act: -0.0001

Data Index: 628419 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2925. Min Act: -0.0000

Data Index: 893055 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2887. Min Act: -0.0001

Data Index: 633894 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2820. Min Act: -0.0001

Data Index: 605045 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2708. Min Act: -0.0000

Data Index: 577839 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2879. Min Act: -0.0001

Data Index: 438724 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2862. Min Act: -0.0000

Data Index: 145603 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2700. Min Act: -0.0000

Data Index: 276598 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2677. Min Act: -0.0000

Data Index: 1277599 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2823. Min Act: -0.0000

Data Index: 289712 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2741. Min Act: -0.0000

Data Index: 514660 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2718. Min Act: -0.0001

Data Index: 533719 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2633. Min Act: -0.0000

Data Index: 985628 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2804. Min Act: -0.0001

Data Index: 20444 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2700. Min Act: -0.0000

Data Index: 1279658 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2688. Min Act: -0.0000

Data Index: 320975 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2685. Min Act: 0.0000

Data Index: 240979 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2690. Min Act: -0.0001

Data Index: 1340180 (C4 (Web Text))

Max Activating Token Index: 797