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

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

Neuron 4604 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3830. Min Range: -2.3830

Max Act: 2.3830. Min Act: -0.0000

Data Index: 242788 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 2.3830. Min Range: -2.3830

Max Act: 2.2521. Min Act: -0.0000

Data Index: 996806 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 2.3830. Min Range: -2.3830

Max Act: 2.0417. Min Act: -0.0000

Data Index: 113427 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 2.3830. Min Range: -2.3830

Max Act: 1.9155. Min Act: -0.0000

Data Index: 1081365 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 2.3830. Min Range: -2.3830

Max Act: 1.8079. Min Act: -0.0000

Data Index: 145050 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 2.3830. Min Range: -2.3830

Max Act: 1.8070. Min Act: -0.0000

Data Index: 1283674 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 2.3830. Min Range: -2.3830

Max Act: 1.8078. Min Act: -0.0000

Data Index: 865298 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 2.3830. Min Range: -2.3830

Max Act: 1.9263. Min Act: -0.0000

Data Index: 1148224 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 2.3830. Min Range: -2.3830

Max Act: 1.7247. Min Act: -0.0000

Data Index: 1307723 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 2.3830. Min Range: -2.3830

Max Act: 1.8186. Min Act: -0.0000

Data Index: 1148256 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 2.3830. Min Range: -2.3830

Max Act: 1.7902. Min Act: -0.0000

Data Index: 43434 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 2.3830. Min Range: -2.3830

Max Act: 1.7638. Min Act: -0.0000

Data Index: 1288864 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 2.3830. Min Range: -2.3830

Max Act: 1.8052. Min Act: -0.0000

Data Index: 874415 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 2.3830. Min Range: -2.3830

Max Act: 1.7089. Min Act: -0.0000

Data Index: 801111 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 2.3830. Min Range: -2.3830

Max Act: 1.7835. Min Act: -0.0000

Data Index: 919000 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 2.3830. Min Range: -2.3830

Max Act: 1.7647. Min Act: -0.0000

Data Index: 82431 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 2.3830. Min Range: -2.3830

Max Act: 1.6869. Min Act: -0.0000

Data Index: 1054812 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 2.3830. Min Range: -2.3830

Max Act: 1.6629. Min Act: -0.0000

Data Index: 797294 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 2.3830. Min Range: -2.3830

Max Act: 1.5674. Min Act: -0.0000

Data Index: 1298704 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 2.3830. Min Range: -2.3830

Max Act: 1.5883. Min Act: -0.0000

Data Index: 911312 (C4 (Web Text))

Max Activating Token Index: 922