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

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

Neuron 3427 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7742. Min Range: -3.7742

Max Act: 3.7742. Min Act: -0.0000

Data Index: 995236 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 3.7742. Min Range: -3.7742

Max Act: 3.6279. Min Act: -0.0000

Data Index: 1037164 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 3.7742. Min Range: -3.7742

Max Act: 3.3684. Min Act: -0.0000

Data Index: 1343738 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 3.7742. Min Range: -3.7742

Max Act: 3.6416. Min Act: -0.0000

Data Index: 1247127 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 3.7742. Min Range: -3.7742

Max Act: 3.1339. Min Act: -0.0000

Data Index: 557049 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 3.7742. Min Range: -3.7742

Max Act: 3.0483. Min Act: -0.0000

Data Index: 467148 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 3.7742. Min Range: -3.7742

Max Act: 2.9013. Min Act: -0.0000

Data Index: 285831 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 3.7742. Min Range: -3.7742

Max Act: 2.9464. Min Act: -0.0000

Data Index: 815156 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 3.7742. Min Range: -3.7742

Max Act: 2.7635. Min Act: -0.0000

Data Index: 1257113 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 3.7742. Min Range: -3.7742

Max Act: 2.8655. Min Act: -0.0000

Data Index: 901502 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 3.7742. Min Range: -3.7742

Max Act: 2.9653. Min Act: -0.0000

Data Index: 777745 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 3.7742. Min Range: -3.7742

Max Act: 2.7880. Min Act: -0.0000

Data Index: 135744 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 3.7742. Min Range: -3.7742

Max Act: 2.6359. Min Act: -0.0000

Data Index: 192469 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 3.7742. Min Range: -3.7742

Max Act: 2.6119. Min Act: -0.0000

Data Index: 1179153 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 3.7742. Min Range: -3.7742

Max Act: 2.4310. Min Act: -0.0000

Data Index: 821183 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 3.7742. Min Range: -3.7742

Max Act: 2.5499. Min Act: -0.0000

Data Index: 400278 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 3.7742. Min Range: -3.7742

Max Act: 2.4853. Min Act: -0.0000

Data Index: 1142839 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 3.7742. Min Range: -3.7742

Max Act: 2.4476. Min Act: -0.0000

Data Index: 810313 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 3.7742. Min Range: -3.7742

Max Act: 2.5723. Min Act: -0.0000

Data Index: 316380 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 3.7742. Min Range: -3.7742

Max Act: 2.4486. Min Act: -0.0000

Data Index: 192955 (C4 (Web Text))

Max Activating Token Index: 284