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

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

Neuron 5312 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.6508. Min Act: -0.0000

Data Index: 395503 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.2424. Min Act: -0.0000

Data Index: 250900 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.1847. Min Act: -0.0000

Data Index: 16514 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.1794. Min Act: -0.0000

Data Index: 251844 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.1009. Min Act: -0.0000

Data Index: 1542030 (Python Code)

Max Activating Token Index: 802

Text #5

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.1387. Min Act: -0.0000

Data Index: 1504496 (Python Code)

Max Activating Token Index: 999

Text #6

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.0283. Min Act: -0.0000

Data Index: 199518 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.0145. Min Act: -0.0000

Data Index: 766380 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.0768. Min Act: -0.0000

Data Index: 305981 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.0678. Min Act: -0.0000

Data Index: 975202 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 1.6508. Min Range: -1.6508

Max Act: 1.0009. Min Act: -0.0000

Data Index: 164153 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 1.6508. Min Range: -1.6508

Max Act: 0.9983. Min Act: -0.0000

Data Index: 810415 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 1.6508. Min Range: -1.6508

Max Act: 0.9319. Min Act: -0.0000

Data Index: 376213 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 1.6508. Min Range: -1.6508

Max Act: 0.9084. Min Act: -0.0000

Data Index: 250286 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 1.6508. Min Range: -1.6508

Max Act: 0.9607. Min Act: -0.0000

Data Index: 338622 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 1.6508. Min Range: -1.6508

Max Act: 0.9519. Min Act: -0.0000

Data Index: 1000057 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 1.6508. Min Range: -1.6508

Max Act: 0.9934. Min Act: -0.0000

Data Index: 560764 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 1.6508. Min Range: -1.6508

Max Act: 0.9050. Min Act: -0.0000

Data Index: 1364091 (Python Code)

Max Activating Token Index: 159

Text #18

Max Range: 1.6508. Min Range: -1.6508

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1267077 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 1.6508. Min Range: -1.6508

Max Act: 0.9261. Min Act: -0.0000

Data Index: 1337589 (C4 (Web Text))

Max Activating Token Index: 168