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

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

Neuron 1547 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.9920. Min Act: -0.1700

Data Index: 127079 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.8670. Min Act: -0.1700

Data Index: 204677 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.8670. Min Act: -0.1700

Data Index: 601168 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.6795. Min Act: -0.1700

Data Index: 291822 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.5545. Min Act: -0.1700

Data Index: 318379 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.6795. Min Act: -0.1700

Data Index: 736061 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.7420. Min Act: -0.1700

Data Index: 851588 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.6795. Min Act: -0.1700

Data Index: 238417 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.6170. Min Act: -0.1700

Data Index: 954595 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.4920. Min Act: -0.1700

Data Index: 473579 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.6795. Min Act: -0.1700

Data Index: 1203635 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.4920. Min Act: -0.1700

Data Index: 486015 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.4920. Min Act: -0.1700

Data Index: 436369 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.4920. Min Act: -0.1700

Data Index: 675739 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.4920. Min Act: -0.1700

Data Index: 1282217 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.6170. Min Act: -0.1700

Data Index: 382663 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.4920. Min Act: -0.1700

Data Index: 754738 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.3670. Min Act: -0.1700

Data Index: 404163 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.3670. Min Act: -0.1700

Data Index: 899074 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 7.9920. Min Range: -7.9920

Max Act: 7.4920. Min Act: -0.1700

Data Index: 923941 (C4 (Web Text))

Max Activating Token Index: 426