Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 959 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.4371. Min Act: -0.0001

Data Index: 481952 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.2091. Min Act: -0.0001

Data Index: 724960 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.2057. Min Act: -0.0001

Data Index: 667993 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.1582. Min Act: -0.0001

Data Index: 597032 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.1300. Min Act: -0.0001

Data Index: 605890 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.2167. Min Act: -0.0001

Data Index: 687024 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.0949. Min Act: -0.0001

Data Index: 608033 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.1599. Min Act: -0.0001

Data Index: 833257 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.0326. Min Act: -0.0001

Data Index: 372806 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.0864. Min Act: -0.0001

Data Index: 445567 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 1.4371. Min Range: -1.4371

Max Act: 0.9888. Min Act: -0.0001

Data Index: 626314 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 1.4371. Min Range: -1.4371

Max Act: 0.9440. Min Act: -0.0001

Data Index: 1319229 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 1.4371. Min Range: -1.4371

Max Act: 1.0086. Min Act: -0.0001

Data Index: 212839 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 1.4371. Min Range: -1.4371

Max Act: 0.8670. Min Act: -0.0001

Data Index: 598487 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 1.4371. Min Range: -1.4371

Max Act: 0.9405. Min Act: -0.0001

Data Index: 948273 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 1.4371. Min Range: -1.4371

Max Act: 0.8579. Min Act: -0.0001

Data Index: 80506 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 1.4371. Min Range: -1.4371

Max Act: 0.9348. Min Act: -0.0001

Data Index: 1137904 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 1.4371. Min Range: -1.4371

Max Act: 0.9630. Min Act: -0.0001

Data Index: 781920 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 1.4371. Min Range: -1.4371

Max Act: 0.9350. Min Act: -0.0001

Data Index: 1188922 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 1.4371. Min Range: -1.4371

Max Act: 0.9291. Min Act: -0.0001

Data Index: 496479 (C4 (Web Text))

Max Activating Token Index: 762