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

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

Neuron 910 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.4009. Min Act: -0.0001

Data Index: 671932 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.4293. Min Act: -0.0000

Data Index: 1079375 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.3860. Min Act: -0.0000

Data Index: 50703 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.3423. Min Act: -0.0000

Data Index: 376524 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.3334. Min Act: -0.0001

Data Index: 122213 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.3181. Min Act: -0.0000

Data Index: 282261 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.1350. Min Act: -0.0000

Data Index: 851907 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.2538. Min Act: -0.0001

Data Index: 686591 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.2018. Min Act: -0.0000

Data Index: 876110 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.2104. Min Act: -0.0000

Data Index: 64953 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.2433. Min Act: -0.0000

Data Index: 683159 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.1900. Min Act: -0.0000

Data Index: 530866 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.0885. Min Act: -0.0000

Data Index: 298028 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.1310. Min Act: -0.0000

Data Index: 386068 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.1099. Min Act: -0.0000

Data Index: 1134994 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.0736. Min Act: -0.0001

Data Index: 653247 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.1025. Min Act: -0.0000

Data Index: 102153 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.0573. Min Act: -0.0000

Data Index: 1117578 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.0871. Min Act: -0.0000

Data Index: 1326672 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 1.4293. Min Range: -1.4293

Max Act: 1.0513. Min Act: -0.0000

Data Index: 453538 (C4 (Web Text))

Max Activating Token Index: 382