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

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

Neuron 2738 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: 0.2224. Min Range: -0.2224

Max Act: 0.2224. Min Act: -0.0001

Data Index: 509073 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 0.2224. Min Range: -0.2224

Max Act: 0.1814. Min Act: -0.0001

Data Index: 525177 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.2224. Min Range: -0.2224

Max Act: 0.1948. Min Act: -0.0001

Data Index: 208355 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 0.2224. Min Range: -0.2224

Max Act: 0.1906. Min Act: -0.0001

Data Index: 2900 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.2224. Min Range: -0.2224

Max Act: 0.1782. Min Act: -0.0001

Data Index: 127987 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 0.2224. Min Range: -0.2224

Max Act: 0.1850. Min Act: -0.0001

Data Index: 1190837 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 0.2224. Min Range: -0.2224

Max Act: 0.1550. Min Act: -0.0001

Data Index: 208334 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 0.2224. Min Range: -0.2224

Max Act: 0.1490. Min Act: -0.0001

Data Index: 946532 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.2224. Min Range: -0.2224

Max Act: 0.1355. Min Act: -0.0001

Data Index: 385633 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.2224. Min Range: -0.2224

Max Act: 0.1525. Min Act: -0.0001

Data Index: 942135 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 0.2224. Min Range: -0.2224

Max Act: 0.1521. Min Act: -0.0001

Data Index: 702105 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.2224. Min Range: -0.2224

Max Act: 0.1477. Min Act: -0.0001

Data Index: 1182009 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.2224. Min Range: -0.2224

Max Act: 0.1397. Min Act: -0.0000

Data Index: 493826 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.2224. Min Range: -0.2224

Max Act: 0.1438. Min Act: -0.0001

Data Index: 214238 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.2224. Min Range: -0.2224

Max Act: 0.1376. Min Act: -0.0001

Data Index: 942291 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.2224. Min Range: -0.2224

Max Act: 0.1324. Min Act: -0.0001

Data Index: 109782 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.2224. Min Range: -0.2224

Max Act: 0.1334. Min Act: -0.0001

Data Index: 895494 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.2224. Min Range: -0.2224

Max Act: 0.1405. Min Act: -0.0001

Data Index: 974045 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.2224. Min Range: -0.2224

Max Act: 0.1353. Min Act: -0.0001

Data Index: 440342 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 0.2224. Min Range: -0.2224

Max Act: 0.1439. Min Act: -0.0001

Data Index: 271949 (C4 (Web Text))

Max Activating Token Index: 164