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

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

Neuron 4628 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.4200. Min Act: -0.0000

Data Index: 470225 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.4122. Min Act: -0.0000

Data Index: 297300 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3961. Min Act: -0.0000

Data Index: 572110 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.3385. Min Act: -0.0000

Data Index: 839078 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2948. Min Act: -0.0000

Data Index: 381011 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2939. Min Act: -0.0000

Data Index: 586654 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2987. Min Act: -0.0000

Data Index: 460103 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2871. Min Act: -0.0000

Data Index: 724236 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2917. Min Act: -0.0000

Data Index: 548429 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2786. Min Act: -0.0000

Data Index: 422852 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2731. Min Act: -0.0000

Data Index: 643792 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2653. Min Act: -0.0000

Data Index: 326795 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2682. Min Act: -0.0000

Data Index: 1180885 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2518. Min Act: -0.0000

Data Index: 250958 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2387. Min Act: -0.0000

Data Index: 316660 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2587. Min Act: -0.0000

Data Index: 242095 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2492. Min Act: -0.0000

Data Index: 32841 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2539. Min Act: -0.0000

Data Index: 208309 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2535. Min Act: -0.0000

Data Index: 761582 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.4200. Min Range: -0.4200

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1135970 (C4 (Web Text))

Max Activating Token Index: 366