Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1045 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.4181. Min Act: -0.1700

Data Index: 1407197 (Python Code)

Max Activating Token Index: 153

Text #1

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.3553. Min Act: -0.1700

Data Index: 1056467 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.2925. Min Act: -0.1700

Data Index: 136123 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.3239. Min Act: -0.1700

Data Index: 1272594 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.2925. Min Act: -0.1700

Data Index: 579092 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.2925. Min Act: -0.1700

Data Index: 1019135 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.2768. Min Act: -0.1700

Data Index: 676864 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.2768. Min Act: -0.1700

Data Index: 783106 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.2925. Min Act: -0.1700

Data Index: 731262 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.2925. Min Act: -0.1700

Data Index: 199006 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.2454. Min Act: -0.1700

Data Index: 1101097 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.2611. Min Act: -0.1700

Data Index: 487922 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.2611. Min Act: -0.1700

Data Index: 853454 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.2611. Min Act: -0.1700

Data Index: 871408 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.2297. Min Act: -0.1700

Data Index: 1544759 (Python Code)

Max Activating Token Index: 848

Text #15

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.2611. Min Act: -0.1700

Data Index: 1352548 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.2611. Min Act: -0.1700

Data Index: 202629 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.1982. Min Act: -0.1700

Data Index: 288319 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.2454. Min Act: -0.1700

Data Index: 796421 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 3.4181. Min Range: -3.4181

Max Act: 3.2139. Min Act: -0.1700

Data Index: 8684 (C4 (Web Text))

Max Activating Token Index: 810