Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5385 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.8280. Min Act: -0.0000

Data Index: 1134914 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.6277. Min Act: -0.0000

Data Index: 927815 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.6395. Min Act: -0.0000

Data Index: 632767 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.6371. Min Act: -0.0000

Data Index: 60497 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.4869. Min Act: -0.0000

Data Index: 399677 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.4355. Min Act: -0.0000

Data Index: 1304431 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.4727. Min Act: -0.0000

Data Index: 1596681 (Python Code)

Max Activating Token Index: 263

Text #7

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.4774. Min Act: -0.0000

Data Index: 1297594 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.4448. Min Act: -0.0000

Data Index: 712221 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.4571. Min Act: -0.0000

Data Index: 730403 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.4390. Min Act: -0.0000

Data Index: 796027 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.5081. Min Act: -0.0000

Data Index: 1108701 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.4138. Min Act: -0.0000

Data Index: 308788 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.5337. Min Act: -0.0000

Data Index: 58870 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.3307. Min Act: -0.0000

Data Index: 857756 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.3905. Min Act: -0.0000

Data Index: 1068680 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.2794. Min Act: -0.0000

Data Index: 266731 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.4731. Min Act: -0.0000

Data Index: 441333 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.3168. Min Act: -0.0000

Data Index: 1073476 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.4564. Min Act: -0.0000

Data Index: 321308 (C4 (Web Text))

Max Activating Token Index: 996