Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4385 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4767. Min Act: -0.0002

Data Index: 1093933 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4000. Min Act: -0.0002

Data Index: 664021 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3739. Min Act: -0.0002

Data Index: 1190875 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3224. Min Act: -0.0002

Data Index: 1062985 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3295. Min Act: -0.0002

Data Index: 6611 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3260. Min Act: -0.0002

Data Index: 841006 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3089. Min Act: -0.0002

Data Index: 446767 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3015. Min Act: -0.0002

Data Index: 215977 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3043. Min Act: -0.0002

Data Index: 1025374 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.2789. Min Act: -0.0002

Data Index: 38480 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.2765. Min Act: -0.0002

Data Index: 1258251 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.2731. Min Act: -0.0002

Data Index: 832319 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.2663. Min Act: -0.0002

Data Index: 705633 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.2699. Min Act: -0.0002

Data Index: 396137 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.2698. Min Act: -0.0002

Data Index: 810412 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.2650. Min Act: -0.0002

Data Index: 848315 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.2548. Min Act: -0.0002

Data Index: 671778 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.2596. Min Act: -0.0002

Data Index: 1335916 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.2590. Min Act: -0.0002

Data Index: 870518 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.2587. Min Act: -0.0002

Data Index: 782510 (C4 (Web Text))

Max Activating Token Index: 286