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

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

Neuron 964 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.4384. Min Act: -0.1700

Data Index: 215172 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.4541. Min Act: -0.1700

Data Index: 824658 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.4227. Min Act: -0.1700

Data Index: 164500 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.3913. Min Act: -0.1700

Data Index: 118733 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.3600. Min Act: -0.1700

Data Index: 571167 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.3913. Min Act: -0.1700

Data Index: 833279 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.3757. Min Act: -0.1700

Data Index: 639024 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.3600. Min Act: -0.1700

Data Index: 616947 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.3286. Min Act: -0.1700

Data Index: 187294 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.3286. Min Act: -0.1700

Data Index: 694655 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.2972. Min Act: -0.1700

Data Index: 223230 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.3129. Min Act: -0.1700

Data Index: 196760 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.3129. Min Act: -0.1700

Data Index: 548137 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.2972. Min Act: -0.1700

Data Index: 773424 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.2972. Min Act: -0.1700

Data Index: 874189 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.2815. Min Act: -0.1700

Data Index: 476290 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.2500. Min Act: -0.1700

Data Index: 810835 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.2658. Min Act: -0.1700

Data Index: 232061 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.2658. Min Act: -0.1700

Data Index: 464983 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 3.4541. Min Range: -3.4541

Max Act: 3.3129. Min Act: -0.1700

Data Index: 159991 (C4 (Web Text))

Max Activating Token Index: 583