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

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

Neuron 15 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: 3.9178. Min Range: -3.9178

Max Act: 3.9178. Min Act: -0.1700

Data Index: 328388 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 3.9178. Min Range: -3.9178

Max Act: 3.9021. Min Act: -0.1700

Data Index: 1237212 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 3.9178. Min Range: -3.9178

Max Act: 3.8552. Min Act: -0.1700

Data Index: 577916 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 3.9178. Min Range: -3.9178

Max Act: 3.8709. Min Act: -0.1700

Data Index: 673537 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 3.9178. Min Range: -3.9178

Max Act: 3.8709. Min Act: -0.1700

Data Index: 841328 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 3.9178. Min Range: -3.9178

Max Act: 3.8552. Min Act: -0.1700

Data Index: 198432 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 3.9178. Min Range: -3.9178

Max Act: 3.8239. Min Act: -0.1700

Data Index: 1263992 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 3.9178. Min Range: -3.9178

Max Act: 3.8396. Min Act: -0.1700

Data Index: 333904 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 3.9178. Min Range: -3.9178

Max Act: 3.8239. Min Act: -0.1700

Data Index: 288455 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 3.9178. Min Range: -3.9178

Max Act: 3.8083. Min Act: -0.1700

Data Index: 1030040 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 3.9178. Min Range: -3.9178

Max Act: 3.8083. Min Act: -0.1700

Data Index: 1356305 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 3.9178. Min Range: -3.9178

Max Act: 3.8239. Min Act: -0.1700

Data Index: 260389 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 3.9178. Min Range: -3.9178

Max Act: 3.8239. Min Act: -0.1700

Data Index: 1194872 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 3.9178. Min Range: -3.9178

Max Act: 3.8239. Min Act: -0.1700

Data Index: 16824 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 3.9178. Min Range: -3.9178

Max Act: 3.7927. Min Act: -0.1700

Data Index: 1070994 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 3.9178. Min Range: -3.9178

Max Act: 3.8083. Min Act: -0.1700

Data Index: 1148477 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 3.9178. Min Range: -3.9178

Max Act: 3.8083. Min Act: -0.1700

Data Index: 213275 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 3.9178. Min Range: -3.9178

Max Act: 3.7927. Min Act: -0.1700

Data Index: 1214245 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 3.9178. Min Range: -3.9178

Max Act: 3.8083. Min Act: -0.1700

Data Index: 463227 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 3.9178. Min Range: -3.9178

Max Act: 3.8239. Min Act: -0.1700

Data Index: 858202 (C4 (Web Text))

Max Activating Token Index: 908