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

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

Neuron 2389 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: 0.3695. Min Range: -0.3695

Max Act: 0.3695. Min Act: -0.0000

Data Index: 57248 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3082. Min Act: -0.0001

Data Index: 667960 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3048. Min Act: -0.0001

Data Index: 802670 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3035. Min Act: -0.0000

Data Index: 683332 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2964. Min Act: -0.0000

Data Index: 361442 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3088. Min Act: -0.0000

Data Index: 781276 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2901. Min Act: -0.0000

Data Index: 177522 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2910. Min Act: -0.0000

Data Index: 27573 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1194776 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2747. Min Act: -0.0000

Data Index: 181936 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2788. Min Act: -0.0001

Data Index: 1343074 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2874. Min Act: -0.0000

Data Index: 99792 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2756. Min Act: -0.0001

Data Index: 476512 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1039306 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2541. Min Act: -0.0000

Data Index: 9526 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1119468 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2606. Min Act: -0.0000

Data Index: 552322 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2614. Min Act: -0.0001

Data Index: 15084 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2533. Min Act: -0.0000

Data Index: 43001 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2602. Min Act: -0.0000

Data Index: 624642 (C4 (Web Text))

Max Activating Token Index: 777