Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2473 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2902. Min Act: -0.0001

Data Index: 275202 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2360. Min Act: -0.0001

Data Index: 513622 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2251. Min Act: -0.0001

Data Index: 327325 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1962. Min Act: -0.0001

Data Index: 281627 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1617. Min Act: -0.0001

Data Index: 513085 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1702. Min Act: -0.0001

Data Index: 1340721 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1597. Min Act: -0.0000

Data Index: 532736 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1395. Min Act: -0.0001

Data Index: 444121 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1619. Min Act: -0.0001

Data Index: 576213 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.0974. Min Act: -0.0000

Data Index: 152020 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1372. Min Act: -0.0000

Data Index: 799204 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1327. Min Act: -0.0001

Data Index: 1096048 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1356. Min Act: -0.0001

Data Index: 960433 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1298. Min Act: -0.0001

Data Index: 1120391 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1280. Min Act: -0.0000

Data Index: 358347 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1305. Min Act: -0.0001

Data Index: 100124 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1301. Min Act: -0.0001

Data Index: 565770 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1300. Min Act: -0.0001

Data Index: 605523 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1256. Min Act: -0.0001

Data Index: 383379 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1059. Min Act: -0.0001

Data Index: 61657 (C4 (Web Text))

Max Activating Token Index: 393