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

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

Neuron 1717 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: 3.3899. Min Range: -3.3899

Max Act: 3.3899. Min Act: -0.1698

Data Index: 337281 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2316. Min Act: -0.1695

Data Index: 749394 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2223. Min Act: -0.1700

Data Index: 789997 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2063. Min Act: -0.1699

Data Index: 729640 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2122. Min Act: -0.1700

Data Index: 1079089 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1940. Min Act: -0.1522

Data Index: 486565 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1509. Min Act: -0.1700

Data Index: 155044 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1418. Min Act: -0.1700

Data Index: 1178274 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1353. Min Act: -0.1673

Data Index: 207110 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1318. Min Act: -0.1700

Data Index: 46263 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1205. Min Act: -0.1700

Data Index: 833334 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1177. Min Act: -0.1630

Data Index: 1047031 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1248. Min Act: -0.1700

Data Index: 83304 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1072. Min Act: -0.1699

Data Index: 277649 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1070. Min Act: -0.1700

Data Index: 476400 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1021. Min Act: -0.1591

Data Index: 989371 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1099. Min Act: -0.1700

Data Index: 178531 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1143. Min Act: -0.1699

Data Index: 759910 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.0967. Min Act: -0.1644

Data Index: 1122404 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.0972. Min Act: -0.1694

Data Index: 1014878 (C4 (Web Text))

Max Activating Token Index: 787