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

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

Neuron 461 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: 4.3007. Min Range: -4.3007

Max Act: 4.3007. Min Act: -0.1700

Data Index: 1042183 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 4.3007. Min Range: -4.3007

Max Act: 4.2315. Min Act: -0.1700

Data Index: 26311 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 4.3007. Min Range: -4.3007

Max Act: 4.1216. Min Act: -0.1700

Data Index: 88149 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 4.3007. Min Range: -4.3007

Max Act: 4.1684. Min Act: -0.1700

Data Index: 1082985 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 4.3007. Min Range: -4.3007

Max Act: 4.1383. Min Act: -0.1700

Data Index: 214262 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 4.3007. Min Range: -4.3007

Max Act: 4.1213. Min Act: -0.1700

Data Index: 15057 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 4.3007. Min Range: -4.3007

Max Act: 4.0328. Min Act: -0.1700

Data Index: 214321 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 4.3007. Min Range: -4.3007

Max Act: 4.0612. Min Act: -0.1700

Data Index: 287353 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 4.3007. Min Range: -4.3007

Max Act: 4.0689. Min Act: -0.1700

Data Index: 301091 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 4.3007. Min Range: -4.3007

Max Act: 4.1086. Min Act: -0.1700

Data Index: 1046165 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 4.3007. Min Range: -4.3007

Max Act: 4.0703. Min Act: -0.1700

Data Index: 1319196 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 4.3007. Min Range: -4.3007

Max Act: 3.9945. Min Act: -0.1700

Data Index: 519422 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 4.3007. Min Range: -4.3007

Max Act: 4.0216. Min Act: -0.1700

Data Index: 699595 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 4.3007. Min Range: -4.3007

Max Act: 3.9675. Min Act: -0.1700

Data Index: 301920 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 4.3007. Min Range: -4.3007

Max Act: 4.0272. Min Act: -0.1700

Data Index: 335753 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 4.3007. Min Range: -4.3007

Max Act: 3.9624. Min Act: -0.1700

Data Index: 1164497 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 4.3007. Min Range: -4.3007

Max Act: 3.9758. Min Act: -0.1700

Data Index: 1168865 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 4.3007. Min Range: -4.3007

Max Act: 3.9923. Min Act: -0.1700

Data Index: 719471 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 4.3007. Min Range: -4.3007

Max Act: 3.9701. Min Act: -0.1700

Data Index: 169600 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 4.3007. Min Range: -4.3007

Max Act: 4.0093. Min Act: -0.1700

Data Index: 1156322 (C4 (Web Text))

Max Activating Token Index: 891