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

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

Neuron 3177 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.8036. Min Act: -0.0000

Data Index: 1395115 (Python Code)

Max Activating Token Index: 244

Text #1

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.8622. Min Act: -0.0000

Data Index: 102024 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.6839. Min Act: -0.0000

Data Index: 900990 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4404. Min Act: -0.0000

Data Index: 666416 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.3528. Min Act: -0.0000

Data Index: 1127860 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.3184. Min Act: -0.0000

Data Index: 384053 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.2824. Min Act: -0.0000

Data Index: 1203858 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.2245. Min Act: -0.0000

Data Index: 73853 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.2341. Min Act: -0.0000

Data Index: 477016 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.1677. Min Act: -0.0000

Data Index: 720680 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.1096. Min Act: -0.0000

Data Index: 1193463 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.0969. Min Act: -0.0000

Data Index: 580146 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.0819. Min Act: -0.0000

Data Index: 470646 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 1.8622. Min Range: -1.8622

Max Act: 0.9796. Min Act: -0.0000

Data Index: 832006 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.0859. Min Act: -0.0000

Data Index: 918923 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.0718. Min Act: -0.0000

Data Index: 139926 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.0061. Min Act: -0.0000

Data Index: 15554 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.1338. Min Act: -0.0000

Data Index: 67659 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.0248. Min Act: -0.0000

Data Index: 100962 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 1.8622. Min Range: -1.8622

Max Act: 0.9911. Min Act: -0.0000

Data Index: 479962 (C4 (Web Text))

Max Activating Token Index: 230