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

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

Neuron 890 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0360. Min Act: -0.0002

Data Index: 192242 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0341. Min Act: -0.0001

Data Index: 615317 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0292. Min Act: -0.0001

Data Index: 700232 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0270. Min Act: -0.0001

Data Index: 181768 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0267. Min Act: -0.0001

Data Index: 838532 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0262. Min Act: -0.0001

Data Index: 893849 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0258. Min Act: -0.0001

Data Index: 419361 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0256. Min Act: -0.0001

Data Index: 800962 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0258. Min Act: -0.0001

Data Index: 68825 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0247. Min Act: -0.0001

Data Index: 411082 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0248. Min Act: -0.0001

Data Index: 1349212 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0245. Min Act: -0.0001

Data Index: 198218 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0244. Min Act: -0.0001

Data Index: 651580 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0239. Min Act: -0.0001

Data Index: 1313900 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0243. Min Act: -0.0001

Data Index: 1217258 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0237. Min Act: -0.0001

Data Index: 89928 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0237. Min Act: -0.0001

Data Index: 441473 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0237. Min Act: -0.0001

Data Index: 56402 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0237. Min Act: -0.0001

Data Index: 88824 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1040020 (C4 (Web Text))

Max Activating Token Index: 69