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

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

Neuron 1604 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0907. Min Range: -1.0907

Max Act: 1.0803. Min Act: -0.0001

Data Index: 1183531 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 1.0907. Min Range: -1.0907

Max Act: 1.0907. Min Act: -0.0001

Data Index: 648276 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.9974. Min Act: -0.0001

Data Index: 253949 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.9791. Min Act: -0.0001

Data Index: 1286059 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 1.0907. Min Range: -1.0907

Max Act: 1.0163. Min Act: -0.0001

Data Index: 624816 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 1.0907. Min Range: -1.0907

Max Act: 1.0236. Min Act: -0.0001

Data Index: 957335 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.9610. Min Act: -0.0001

Data Index: 308538 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.9308. Min Act: -0.0001

Data Index: 541784 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.8633. Min Act: -0.0001

Data Index: 220263 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.8525. Min Act: -0.0001

Data Index: 1115871 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.8629. Min Act: -0.0001

Data Index: 480355 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.8605. Min Act: -0.0001

Data Index: 757306 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.8549. Min Act: -0.0001

Data Index: 12930 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.8365. Min Act: -0.0001

Data Index: 323614 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.8865. Min Act: -0.0001

Data Index: 1293719 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.8221. Min Act: -0.0001

Data Index: 1085801 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.8426. Min Act: -0.0001

Data Index: 36618 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.7712. Min Act: -0.0001

Data Index: 1239924 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.7869. Min Act: -0.0001

Data Index: 802006 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.7957. Min Act: -0.0001

Data Index: 1038308 (C4 (Web Text))

Max Activating Token Index: 493