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

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

Neuron 832 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: 0.9832. Min Range: -0.9832

Max Act: 0.9832. Min Act: -0.0000

Data Index: 993585 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.6559. Min Act: -0.0001

Data Index: 832331 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.6055. Min Act: -0.0000

Data Index: 242873 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1307847 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.5406. Min Act: -0.0000

Data Index: 803073 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.4994. Min Act: -0.0001

Data Index: 264045 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.5217. Min Act: -0.0001

Data Index: 384378 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.4986. Min Act: -0.0001

Data Index: 331163 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.4687. Min Act: -0.0001

Data Index: 113229 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.4647. Min Act: -0.0001

Data Index: 9472 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.4631. Min Act: -0.0000

Data Index: 992180 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.4859. Min Act: -0.0000

Data Index: 47125 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.4462. Min Act: -0.0001

Data Index: 846953 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.4443. Min Act: -0.0000

Data Index: 604134 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.3974. Min Act: -0.0001

Data Index: 467346 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.4210. Min Act: -0.0000

Data Index: 855501 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.4444. Min Act: -0.0000

Data Index: 1287523 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.4216. Min Act: -0.0000

Data Index: 191334 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1008950 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.9832. Min Range: -0.9832

Max Act: 0.4066. Min Act: -0.0000

Data Index: 12353 (C4 (Web Text))

Max Activating Token Index: 402