Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 425 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.8397. Min Act: -0.1700

Data Index: 136618 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.7459. Min Act: -0.1700

Data Index: 478134 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.7459. Min Act: -0.1700

Data Index: 1210723 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.7146. Min Act: -0.1700

Data Index: 1170189 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.6520. Min Act: -0.1700

Data Index: 862610 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.6520. Min Act: -0.1700

Data Index: 913429 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.6207. Min Act: -0.1700

Data Index: 1075635 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.6207. Min Act: -0.1700

Data Index: 607198 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.6207. Min Act: -0.1700

Data Index: 467059 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.5580. Min Act: -0.1700

Data Index: 37095 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.5893. Min Act: -0.1700

Data Index: 98886 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.4954. Min Act: -0.1700

Data Index: 1359614 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.5267. Min Act: -0.1700

Data Index: 112335 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.5267. Min Act: -0.1700

Data Index: 933099 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.5267. Min Act: -0.1700

Data Index: 1061335 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.5580. Min Act: -0.1700

Data Index: 509266 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.4954. Min Act: -0.1700

Data Index: 363215 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.4954. Min Act: -0.1700

Data Index: 1202867 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.5267. Min Act: -0.1700

Data Index: 958777 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.4954. Min Act: -0.1700

Data Index: 218288 (C4 (Web Text))

Max Activating Token Index: 339