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

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

Neuron 623 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: 3.8227. Min Range: -3.8227

Max Act: 3.8227. Min Act: -0.1700

Data Index: 1400280 (Python Code)

Max Activating Token Index: 593

Text #1

Max Range: 3.8227. Min Range: -3.8227

Max Act: 3.7816. Min Act: -0.1700

Data Index: 1510826 (Python Code)

Max Activating Token Index: 475

Text #2

Max Range: 3.8227. Min Range: -3.8227

Max Act: 3.7508. Min Act: -0.1700

Data Index: 1115314 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 3.8227. Min Range: -3.8227

Max Act: 3.7263. Min Act: -0.1700

Data Index: 1482787 (Python Code)

Max Activating Token Index: 253

Text #4

Max Range: 3.8227. Min Range: -3.8227

Max Act: 3.7440. Min Act: -0.1700

Data Index: 1564708 (Python Code)

Max Activating Token Index: 365

Text #5

Max Range: 3.8227. Min Range: -3.8227

Max Act: 3.7435. Min Act: -0.1700

Data Index: 1570125 (Python Code)

Max Activating Token Index: 448

Text #6

Max Range: 3.8227. Min Range: -3.8227

Max Act: 3.7280. Min Act: -0.1700

Data Index: 1479103 (Python Code)

Max Activating Token Index: 684

Text #7

Max Range: 3.8227. Min Range: -3.8227

Max Act: 3.7246. Min Act: -0.1700

Data Index: 1425812 (Python Code)

Max Activating Token Index: 32

Text #8

Max Range: 3.8227. Min Range: -3.8227

Max Act: 3.7500. Min Act: -0.1700

Data Index: 1495316 (Python Code)

Max Activating Token Index: 52

Text #9

Max Range: 3.8227. Min Range: -3.8227

Max Act: 3.7187. Min Act: -0.1700

Data Index: 1555759 (Python Code)

Max Activating Token Index: 382

Text #10

Max Range: 3.8227. Min Range: -3.8227

Max Act: 3.6724. Min Act: -0.1700

Data Index: 972835 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 3.8227. Min Range: -3.8227

Max Act: 3.7106. Min Act: -0.1700

Data Index: 1611250 (Python Code)

Max Activating Token Index: 780

Text #12

Max Range: 3.8227. Min Range: -3.8227

Max Act: 3.6733. Min Act: -0.1700

Data Index: 1636886 (Python Code)

Max Activating Token Index: 413

Text #13

Max Range: 3.8227. Min Range: -3.8227

Max Act: 3.6737. Min Act: -0.1700

Data Index: 1409217 (Python Code)

Max Activating Token Index: 519

Text #14

Max Range: 3.8227. Min Range: -3.8227

Max Act: 3.6751. Min Act: -0.1700

Data Index: 1603691 (Python Code)

Max Activating Token Index: 21

Text #15

Max Range: 3.8227. Min Range: -3.8227

Max Act: 3.6804. Min Act: -0.1700

Data Index: 1478895 (Python Code)

Max Activating Token Index: 805

Text #16

Max Range: 3.8227. Min Range: -3.8227

Max Act: 3.6650. Min Act: -0.1700

Data Index: 1425053 (Python Code)

Max Activating Token Index: 43

Text #17

Max Range: 3.8227. Min Range: -3.8227

Max Act: 3.6611. Min Act: -0.1700

Data Index: 1404492 (Python Code)

Max Activating Token Index: 908

Text #18

Max Range: 3.8227. Min Range: -3.8227

Max Act: 3.6365. Min Act: -0.1700

Data Index: 1508996 (Python Code)

Max Activating Token Index: 217

Text #19

Max Range: 3.8227. Min Range: -3.8227

Max Act: 3.6435. Min Act: -0.1700

Data Index: 1398032 (Python Code)

Max Activating Token Index: 743