Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1433 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1709. Min Act: -0.0004

Data Index: 697929 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1610. Min Act: -0.0003

Data Index: 243367 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1519. Min Act: -0.0003

Data Index: 966825 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1565. Min Act: -0.0003

Data Index: 292626 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1623. Min Act: -0.0003

Data Index: 193352 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1507. Min Act: -0.0003

Data Index: 819275 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1558. Min Act: -0.0003

Data Index: 392837 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1521. Min Act: -0.0003

Data Index: 853963 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1536. Min Act: -0.0004

Data Index: 846226 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1525. Min Act: -0.0003

Data Index: 1287506 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1470. Min Act: -0.0003

Data Index: 545428 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1419. Min Act: -0.0003

Data Index: 583105 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1341. Min Act: -0.0003

Data Index: 36870 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1410. Min Act: -0.0003

Data Index: 39010 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1236. Min Act: -0.0003

Data Index: 121245 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1299. Min Act: -0.0003

Data Index: 550322 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1483. Min Act: -0.0003

Data Index: 443243 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1321. Min Act: -0.0003

Data Index: 1154036 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1306. Min Act: -0.0003

Data Index: 676169 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.1709. Min Range: -0.1709

Max Act: 0.1452. Min Act: -0.0003

Data Index: 384231 (C4 (Web Text))

Max Activating Token Index: 989