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

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

Neuron 3381 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0308. Min Range: -1.0308

Max Act: 1.0308. Min Act: -0.0001

Data Index: 530375 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.9966. Min Act: -0.0001

Data Index: 527463 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.8362. Min Act: -0.0001

Data Index: 639921 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7417. Min Act: -0.0001

Data Index: 1290207 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.9924. Min Act: -0.0001

Data Index: 580712 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7778. Min Act: -0.0001

Data Index: 369058 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7649. Min Act: -0.0001

Data Index: 297044 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7767. Min Act: -0.0001

Data Index: 552529 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.8007. Min Act: -0.0001

Data Index: 876251 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7928. Min Act: -0.0001

Data Index: 903892 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7709. Min Act: -0.0001

Data Index: 992240 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7456. Min Act: -0.0001

Data Index: 1043730 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7250. Min Act: -0.0001

Data Index: 1284034 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.8119. Min Act: -0.0001

Data Index: 81791 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7181. Min Act: -0.0001

Data Index: 678860 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.6742. Min Act: -0.0001

Data Index: 87665 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7687. Min Act: -0.0001

Data Index: 964191 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.6900. Min Act: -0.0002

Data Index: 426621 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.6196. Min Act: -0.0002

Data Index: 1290116 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.6608. Min Act: -0.0001

Data Index: 870880 (C4 (Web Text))

Max Activating Token Index: 683