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

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

Neuron 2702 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.5585. Min Act: -0.0001

Data Index: 211655 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.5435. Min Act: -0.0000

Data Index: 734117 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.5286. Min Act: -0.0000

Data Index: 520031 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.3984. Min Act: -0.0000

Data Index: 882611 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.3901. Min Act: -0.0000

Data Index: 1350473 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.2792. Min Act: -0.0000

Data Index: 752634 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.3297. Min Act: -0.0000

Data Index: 71822 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.3183. Min Act: -0.0000

Data Index: 421430 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.3588. Min Act: -0.0000

Data Index: 485526 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.2513. Min Act: -0.0000

Data Index: 164571 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.2569. Min Act: -0.0000

Data Index: 142572 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.2842. Min Act: -0.0000

Data Index: 922618 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.2817. Min Act: -0.0000

Data Index: 986827 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.2951. Min Act: -0.0000

Data Index: 193722 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.2766. Min Act: -0.0000

Data Index: 433574 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.2884. Min Act: -0.0000

Data Index: 1165018 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.1664. Min Act: -0.0000

Data Index: 932630 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.2324. Min Act: -0.0000

Data Index: 722080 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.2676. Min Act: -0.0000

Data Index: 1238983 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.1964. Min Act: -0.0000

Data Index: 982530 (C4 (Web Text))

Max Activating Token Index: 664