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

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

Neuron 1989 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0678. Min Act: -0.0000

Data Index: 979473 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0568. Min Act: -0.0000

Data Index: 13946 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0513. Min Act: -0.0000

Data Index: 754305 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0450. Min Act: -0.0000

Data Index: 812911 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0370. Min Act: -0.0001

Data Index: 818976 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0365. Min Act: -0.0000

Data Index: 946343 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0359. Min Act: -0.0000

Data Index: 753480 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0359. Min Act: -0.0000

Data Index: 137801 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0336. Min Act: -0.0001

Data Index: 15982 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0377. Min Act: -0.0000

Data Index: 81281 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0319. Min Act: -0.0000

Data Index: 1299275 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0328. Min Act: -0.0001

Data Index: 1286989 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0330. Min Act: -0.0001

Data Index: 538718 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0325. Min Act: -0.0000

Data Index: 963138 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0316. Min Act: -0.0001

Data Index: 1331453 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0277. Min Act: -0.0001

Data Index: 657971 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0300. Min Act: -0.0000

Data Index: 1319288 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0278. Min Act: -0.0000

Data Index: 1254900 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0297. Min Act: -0.0001

Data Index: 959455 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0285. Min Act: -0.0000

Data Index: 536308 (C4 (Web Text))

Max Activating Token Index: 166