Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1256 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.3068. Min Act: -0.0002

Data Index: 550537 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2966. Min Act: -0.0003

Data Index: 869353 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2949. Min Act: -0.0003

Data Index: 193991 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2864. Min Act: -0.0003

Data Index: 1278100 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2758. Min Act: -0.0002

Data Index: 452197 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2708. Min Act: -0.0002

Data Index: 465886 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2677. Min Act: -0.0002

Data Index: 1147308 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2723. Min Act: -0.0002

Data Index: 216886 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2615. Min Act: -0.0002

Data Index: 596383 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2596. Min Act: -0.0002

Data Index: 1088117 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2576. Min Act: -0.0002

Data Index: 381699 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2564. Min Act: 0.0004

Data Index: 1281416 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2627. Min Act: -0.0002

Data Index: 95620 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2433. Min Act: -0.0003

Data Index: 199850 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2508. Min Act: -0.0002

Data Index: 203988 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2592. Min Act: -0.0003

Data Index: 461972 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2578. Min Act: -0.0002

Data Index: 9222 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2440. Min Act: -0.0003

Data Index: 752535 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2439. Min Act: -0.0002

Data Index: 239481 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2434. Min Act: -0.0002

Data Index: 1241719 (C4 (Web Text))

Max Activating Token Index: 955