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

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

Neuron 1876 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: 3.3424. Min Range: -3.3424

Max Act: 3.3267. Min Act: -0.1700

Data Index: 1479361 (Python Code)

Max Activating Token Index: 229

Text #1

Max Range: 3.3424. Min Range: -3.3424

Max Act: 3.3424. Min Act: -0.1700

Data Index: 1612187 (Python Code)

Max Activating Token Index: 574

Text #2

Max Range: 3.3424. Min Range: -3.3424

Max Act: 3.2796. Min Act: -0.1700

Data Index: 1426513 (Python Code)

Max Activating Token Index: 978

Text #3

Max Range: 3.3424. Min Range: -3.3424

Max Act: 3.2010. Min Act: -0.1700

Data Index: 1522732 (Python Code)

Max Activating Token Index: 503

Text #4

Max Range: 3.3424. Min Range: -3.3424

Max Act: 3.2167. Min Act: -0.1700

Data Index: 1596447 (Python Code)

Max Activating Token Index: 545

Text #5

Max Range: 3.3424. Min Range: -3.3424

Max Act: 3.2010. Min Act: -0.1700

Data Index: 1635474 (Python Code)

Max Activating Token Index: 186

Text #6

Max Range: 3.3424. Min Range: -3.3424

Max Act: 3.2010. Min Act: -0.1700

Data Index: 1625045 (Python Code)

Max Activating Token Index: 555

Text #7

Max Range: 3.3424. Min Range: -3.3424

Max Act: 3.1380. Min Act: -0.1700

Data Index: 1586173 (Python Code)

Max Activating Token Index: 448

Text #8

Max Range: 3.3424. Min Range: -3.3424

Max Act: 3.1380. Min Act: -0.1700

Data Index: 1477233 (Python Code)

Max Activating Token Index: 215

Text #9

Max Range: 3.3424. Min Range: -3.3424

Max Act: 3.1537. Min Act: -0.1700

Data Index: 1391113 (Python Code)

Max Activating Token Index: 962

Text #10

Max Range: 3.3424. Min Range: -3.3424

Max Act: 3.0749. Min Act: -0.1700

Data Index: 1605412 (Python Code)

Max Activating Token Index: 338

Text #11

Max Range: 3.3424. Min Range: -3.3424

Max Act: 3.0907. Min Act: -0.1700

Data Index: 1653485 (Python Code)

Max Activating Token Index: 118

Text #12

Max Range: 3.3424. Min Range: -3.3424

Max Act: 3.1065. Min Act: -0.1700

Data Index: 1369032 (Python Code)

Max Activating Token Index: 265

Text #13

Max Range: 3.3424. Min Range: -3.3424

Max Act: 3.1222. Min Act: -0.1700

Data Index: 1436703 (Python Code)

Max Activating Token Index: 517

Text #14

Max Range: 3.3424. Min Range: -3.3424

Max Act: 3.1065. Min Act: -0.1700

Data Index: 1441630 (Python Code)

Max Activating Token Index: 994

Text #15

Max Range: 3.3424. Min Range: -3.3424

Max Act: 3.0434. Min Act: -0.1700

Data Index: 1433607 (Python Code)

Max Activating Token Index: 762

Text #16

Max Range: 3.3424. Min Range: -3.3424

Max Act: 3.0434. Min Act: -0.1700

Data Index: 401078 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 3.3424. Min Range: -3.3424

Max Act: 2.9960. Min Act: -0.1700

Data Index: 1469406 (Python Code)

Max Activating Token Index: 553

Text #18

Max Range: 3.3424. Min Range: -3.3424

Max Act: 3.0434. Min Act: -0.1700

Data Index: 1189138 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 3.3424. Min Range: -3.3424

Max Act: 2.9010. Min Act: -0.1700

Data Index: 1476270 (Python Code)

Max Activating Token Index: 891