Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2296 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1401. Min Range: -1.1401

Max Act: 1.1401. Min Act: -0.0001

Data Index: 517729 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 1.1401. Min Range: -1.1401

Max Act: 1.0104. Min Act: -0.0001

Data Index: 206194 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 1.1401. Min Range: -1.1401

Max Act: 1.0017. Min Act: -0.0001

Data Index: 99059 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8443. Min Act: -0.0001

Data Index: 140481 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8388. Min Act: -0.0001

Data Index: 1118872 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.9070. Min Act: -0.0001

Data Index: 1342409 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8775. Min Act: -0.0001

Data Index: 658195 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8657. Min Act: -0.0001

Data Index: 1337504 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8711. Min Act: -0.0001

Data Index: 456809 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8001. Min Act: -0.0001

Data Index: 1254963 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7505. Min Act: -0.0001

Data Index: 1155413 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8385. Min Act: -0.0001

Data Index: 580354 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8128. Min Act: -0.0001

Data Index: 970309 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7659. Min Act: -0.0001

Data Index: 490134 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7786. Min Act: -0.0001

Data Index: 737781 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7532. Min Act: -0.0001

Data Index: 470097 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7254. Min Act: -0.0001

Data Index: 1148817 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7372. Min Act: -0.0001

Data Index: 1346116 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7397. Min Act: -0.0001

Data Index: 96375 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.7006. Min Act: -0.0001

Data Index: 295416 (C4 (Web Text))

Max Activating Token Index: 644