Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 738 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.6124. Min Act: -0.1699

Data Index: 1459171 (Python Code)

Max Activating Token Index: 411

Text #1

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.6043. Min Act: -0.1699

Data Index: 1540928 (Python Code)

Max Activating Token Index: 389

Text #2

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.5336. Min Act: -0.1682

Data Index: 1385031 (Python Code)

Max Activating Token Index: 900

Text #3

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.4431. Min Act: -0.1700

Data Index: 1219406 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.4231. Min Act: -0.1700

Data Index: 1501525 (Python Code)

Max Activating Token Index: 853

Text #5

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.4273. Min Act: -0.1700

Data Index: 1553906 (Python Code)

Max Activating Token Index: 949

Text #6

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.4025. Min Act: -0.1698

Data Index: 1624592 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.3919. Min Act: -0.1700

Data Index: 1519804 (Python Code)

Max Activating Token Index: 289

Text #8

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.3792. Min Act: -0.1699

Data Index: 1573032 (Python Code)

Max Activating Token Index: 725

Text #9

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.3589. Min Act: -0.1700

Data Index: 153985 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.3731. Min Act: -0.1699

Data Index: 1610227 (Python Code)

Max Activating Token Index: 342

Text #11

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.3318. Min Act: -0.1700

Data Index: 389652 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.3115. Min Act: -0.1700

Data Index: 1448204 (Python Code)

Max Activating Token Index: 361

Text #13

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.2997. Min Act: -0.1699

Data Index: 1495135 (Python Code)

Max Activating Token Index: 609

Text #14

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.3016. Min Act: -0.1700

Data Index: 1398812 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.2932. Min Act: -0.1700

Data Index: 1570036 (Python Code)

Max Activating Token Index: 171

Text #16

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.2741. Min Act: -0.1700

Data Index: 1421911 (Python Code)

Max Activating Token Index: 645

Text #17

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.2862. Min Act: -0.1700

Data Index: 1384255 (Python Code)

Max Activating Token Index: 913

Text #18

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.2740. Min Act: -0.1699

Data Index: 1526633 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 4.6124. Min Range: -4.6124

Max Act: 4.2628. Min Act: -0.1700

Data Index: 1528685 (Python Code)

Max Activating Token Index: 286