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

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

Neuron 1333 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.2129. Min Act: -0.1700

Data Index: 222433 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.2286. Min Act: -0.1700

Data Index: 186888 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.1972. Min Act: -0.1700

Data Index: 1213211 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.2129. Min Act: -0.1700

Data Index: 1138153 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.1814. Min Act: -0.1700

Data Index: 736448 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.1657. Min Act: -0.1700

Data Index: 45006 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.1499. Min Act: -0.1700

Data Index: 380066 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.1184. Min Act: -0.1700

Data Index: 809066 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.1499. Min Act: -0.1700

Data Index: 809287 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.1342. Min Act: -0.1700

Data Index: 679291 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.1499. Min Act: -0.1700

Data Index: 332464 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.1027. Min Act: -0.1700

Data Index: 881466 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.1184. Min Act: -0.1700

Data Index: 599208 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.1027. Min Act: -0.1700

Data Index: 987768 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.1027. Min Act: -0.1700

Data Index: 240261 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.1342. Min Act: -0.1700

Data Index: 873168 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.1184. Min Act: -0.1700

Data Index: 701351 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.1184. Min Act: -0.1700

Data Index: 159035 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.1027. Min Act: -0.1700

Data Index: 811236 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 3.2286. Min Range: -3.2286

Max Act: 3.1027. Min Act: -0.1700

Data Index: 1057771 (C4 (Web Text))

Max Activating Token Index: 949