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

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

Neuron 2488 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: 0.5692. Min Range: -0.5692

Max Act: 0.5236. Min Act: -0.0000

Data Index: 446016 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.5692. Min Act: -0.0001

Data Index: 1099390 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.5458. Min Act: -0.0001

Data Index: 518042 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.5001. Min Act: -0.0000

Data Index: 238725 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3858. Min Act: -0.0001

Data Index: 113771 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3845. Min Act: -0.0000

Data Index: 880684 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.4066. Min Act: -0.0000

Data Index: 325508 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.4012. Min Act: -0.0000

Data Index: 425017 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3748. Min Act: -0.0000

Data Index: 897589 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3657. Min Act: -0.0001

Data Index: 425794 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1318137 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3527. Min Act: -0.0000

Data Index: 1351387 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3467. Min Act: -0.0000

Data Index: 417760 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3515. Min Act: -0.0001

Data Index: 450726 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3258. Min Act: -0.0000

Data Index: 849150 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3310. Min Act: -0.0000

Data Index: 994287 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3140. Min Act: -0.0000

Data Index: 335771 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3125. Min Act: -0.0000

Data Index: 1063183 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1012859 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.2974. Min Act: -0.0000

Data Index: 275673 (C4 (Web Text))

Max Activating Token Index: 412