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

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

Neuron 2036 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: 3.3775. Min Range: -3.3775

Max Act: 3.3775. Min Act: -0.1700

Data Index: 1453229 (Python Code)

Max Activating Token Index: 163

Text #1

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.3459. Min Act: -0.1700

Data Index: 742286 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.3228. Min Act: -0.1700

Data Index: 1501278 (Python Code)

Max Activating Token Index: 650

Text #3

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.2810. Min Act: -0.1700

Data Index: 364363 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.2549. Min Act: -0.1700

Data Index: 1037231 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.2433. Min Act: -0.1700

Data Index: 761771 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.2361. Min Act: -0.1700

Data Index: 1278438 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.2339. Min Act: -0.1700

Data Index: 156000 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.2059. Min Act: -0.1700

Data Index: 123154 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.1865. Min Act: -0.1700

Data Index: 1394603 (Python Code)

Max Activating Token Index: 602

Text #10

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.2044. Min Act: -0.1700

Data Index: 773183 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.1840. Min Act: -0.1700

Data Index: 611590 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.1780. Min Act: -0.1700

Data Index: 1224123 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.1797. Min Act: -0.1700

Data Index: 457897 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.1666. Min Act: -0.1700

Data Index: 238025 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.1815. Min Act: -0.1700

Data Index: 537815 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.1772. Min Act: -0.1700

Data Index: 1571891 (Python Code)

Max Activating Token Index: 283

Text #17

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.1798. Min Act: -0.1700

Data Index: 803916 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.1817. Min Act: -0.1700

Data Index: 645285 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 3.3775. Min Range: -3.3775

Max Act: 3.1551. Min Act: -0.1700

Data Index: 1543883 (Python Code)

Max Activating Token Index: 149