Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 538 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.1731. Min Act: -0.0001

Data Index: 1439075 (Python Code)

Max Activating Token Index: 441

Text #1

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.0862. Min Act: -0.0001

Data Index: 1651524 (Python Code)

Max Activating Token Index: 951

Text #2

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.1776. Min Act: -0.0001

Data Index: 1500092 (Python Code)

Max Activating Token Index: 654

Text #3

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.0836. Min Act: -0.0001

Data Index: 1580037 (Python Code)

Max Activating Token Index: 71

Text #4

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.1232. Min Act: -0.0001

Data Index: 1544255 (Python Code)

Max Activating Token Index: 784

Text #5

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.1558. Min Act: -0.0001

Data Index: 1592892 (Python Code)

Max Activating Token Index: 539

Text #6

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.1329. Min Act: -0.0001

Data Index: 1475273 (Python Code)

Max Activating Token Index: 190

Text #7

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.0996. Min Act: -0.0001

Data Index: 1557111 (Python Code)

Max Activating Token Index: 62

Text #8

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.0225. Min Act: -0.0001

Data Index: 1383565 (Python Code)

Max Activating Token Index: 493

Text #9

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.0032. Min Act: -0.0001

Data Index: 1456822 (Python Code)

Max Activating Token Index: 291

Text #10

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.0036. Min Act: -0.0001

Data Index: 1499755 (Python Code)

Max Activating Token Index: 162

Text #11

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.0866. Min Act: -0.0001

Data Index: 1364954 (Python Code)

Max Activating Token Index: 665

Text #12

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.0218. Min Act: -0.0001

Data Index: 1468657 (Python Code)

Max Activating Token Index: 495

Text #13

Max Range: 1.1776. Min Range: -1.1776

Max Act: 0.9895. Min Act: -0.0001

Data Index: 1420206 (Python Code)

Max Activating Token Index: 512

Text #14

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.0193. Min Act: -0.0001

Data Index: 1529962 (Python Code)

Max Activating Token Index: 302

Text #15

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.0062. Min Act: -0.0001

Data Index: 1533463 (Python Code)

Max Activating Token Index: 562

Text #16

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.0683. Min Act: -0.0001

Data Index: 1548900 (Python Code)

Max Activating Token Index: 152

Text #17

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.0062. Min Act: -0.0001

Data Index: 1538733 (Python Code)

Max Activating Token Index: 481

Text #18

Max Range: 1.1776. Min Range: -1.1776

Max Act: 1.0093. Min Act: -0.0001

Data Index: 1490135 (Python Code)

Max Activating Token Index: 665

Text #19

Max Range: 1.1776. Min Range: -1.1776

Max Act: 0.8899. Min Act: -0.0001

Data Index: 1490844 (Python Code)

Max Activating Token Index: 1022