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

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

Neuron 4408 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: 0.2246. Min Range: -0.2246

Max Act: 0.2246. Min Act: -0.0001

Data Index: 759514 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.2096. Min Act: -0.0001

Data Index: 1216644 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1938. Min Act: -0.0000

Data Index: 675156 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1864. Min Act: -0.0001

Data Index: 1049160 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1302846 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1569. Min Act: -0.0001

Data Index: 165087 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1969. Min Act: -0.0001

Data Index: 776135 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1445. Min Act: -0.0001

Data Index: 385335 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1458. Min Act: -0.0001

Data Index: 996994 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1597. Min Act: -0.0001

Data Index: 384456 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1642. Min Act: -0.0001

Data Index: 69798 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1393. Min Act: -0.0001

Data Index: 984444 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1431. Min Act: -0.0001

Data Index: 997886 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1469. Min Act: -0.0000

Data Index: 733316 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1323. Min Act: -0.0000

Data Index: 833332 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1401. Min Act: -0.0001

Data Index: 729834 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1250. Min Act: -0.0000

Data Index: 724652 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1410. Min Act: -0.0001

Data Index: 100601 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1334. Min Act: -0.0001

Data Index: 1195355 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 0.2246. Min Range: -0.2246

Max Act: 0.1277. Min Act: -0.0000

Data Index: 399866 (C4 (Web Text))

Max Activating Token Index: 826