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

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

Neuron 1819 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2181. Min Range: -4.2181

Max Act: 4.2181. Min Act: -0.1700

Data Index: 1510675 (Python Code)

Max Activating Token Index: 854

Text #1

Max Range: 4.2181. Min Range: -4.2181

Max Act: 3.9367. Min Act: -0.1700

Data Index: 391442 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 4.2181. Min Range: -4.2181

Max Act: 3.9367. Min Act: -0.1700

Data Index: 367376 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 4.2181. Min Range: -4.2181

Max Act: 3.9367. Min Act: -0.1700

Data Index: 529583 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 4.2181. Min Range: -4.2181

Max Act: 3.9054. Min Act: -0.1700

Data Index: 241893 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 4.2181. Min Range: -4.2181

Max Act: 3.8742. Min Act: -0.1700

Data Index: 178616 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 4.2181. Min Range: -4.2181

Max Act: 3.8742. Min Act: -0.1700

Data Index: 529909 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 4.2181. Min Range: -4.2181

Max Act: 3.8742. Min Act: -0.1700

Data Index: 1505151 (Python Code)

Max Activating Token Index: 275

Text #8

Max Range: 4.2181. Min Range: -4.2181

Max Act: 3.8429. Min Act: -0.1700

Data Index: 1420597 (Python Code)

Max Activating Token Index: 316

Text #9

Max Range: 4.2181. Min Range: -4.2181

Max Act: 3.8742. Min Act: -0.1700

Data Index: 196392 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 4.2181. Min Range: -4.2181

Max Act: 3.8742. Min Act: -0.1700

Data Index: 1149689 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 4.2181. Min Range: -4.2181

Max Act: 3.8429. Min Act: -0.1700

Data Index: 161622 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 4.2181. Min Range: -4.2181

Max Act: 3.7803. Min Act: -0.1700

Data Index: 1219476 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 4.2181. Min Range: -4.2181

Max Act: 3.8742. Min Act: -0.1700

Data Index: 909967 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 4.2181. Min Range: -4.2181

Max Act: 3.8429. Min Act: -0.1700

Data Index: 748084 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 4.2181. Min Range: -4.2181

Max Act: 3.8116. Min Act: -0.1700

Data Index: 609889 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 4.2181. Min Range: -4.2181

Max Act: 3.7803. Min Act: -0.1700

Data Index: 636371 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 4.2181. Min Range: -4.2181

Max Act: 3.8429. Min Act: -0.1700

Data Index: 1058971 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 4.2181. Min Range: -4.2181

Max Act: 3.8116. Min Act: -0.1700

Data Index: 906700 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 4.2181. Min Range: -4.2181

Max Act: 3.8116. Min Act: -0.1700

Data Index: 1181881 (C4 (Web Text))

Max Activating Token Index: 238