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

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

Neuron 613 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4802. Min Range: -5.4802

Max Act: 5.4802. Min Act: -0.1700

Data Index: 1643003 (Python Code)

Max Activating Token Index: 188

Text #1

Max Range: 5.4802. Min Range: -5.4802

Max Act: 5.4177. Min Act: -0.1700

Data Index: 1389642 (Python Code)

Max Activating Token Index: 419

Text #2

Max Range: 5.4802. Min Range: -5.4802

Max Act: 5.3865. Min Act: -0.1700

Data Index: 1590654 (Python Code)

Max Activating Token Index: 115

Text #3

Max Range: 5.4802. Min Range: -5.4802

Max Act: 5.3552. Min Act: -0.1700

Data Index: 1447273 (Python Code)

Max Activating Token Index: 246

Text #4

Max Range: 5.4802. Min Range: -5.4802

Max Act: 5.3865. Min Act: -0.1700

Data Index: 1577704 (Python Code)

Max Activating Token Index: 49

Text #5

Max Range: 5.4802. Min Range: -5.4802

Max Act: 5.3865. Min Act: -0.1700

Data Index: 1432195 (Python Code)

Max Activating Token Index: 747

Text #6

Max Range: 5.4802. Min Range: -5.4802

Max Act: 5.3240. Min Act: -0.1700

Data Index: 1583568 (Python Code)

Max Activating Token Index: 134

Text #7

Max Range: 5.4802. Min Range: -5.4802

Max Act: 5.3552. Min Act: -0.1700

Data Index: 1547807 (Python Code)

Max Activating Token Index: 1021

Text #8

Max Range: 5.4802. Min Range: -5.4802

Max Act: 5.2927. Min Act: -0.1700

Data Index: 1571324 (Python Code)

Max Activating Token Index: 403

Text #9

Max Range: 5.4802. Min Range: -5.4802

Max Act: 5.1677. Min Act: -0.1700

Data Index: 1391733 (Python Code)

Max Activating Token Index: 291

Text #10

Max Range: 5.4802. Min Range: -5.4802

Max Act: 5.1052. Min Act: -0.1700

Data Index: 1504316 (Python Code)

Max Activating Token Index: 388

Text #11

Max Range: 5.4802. Min Range: -5.4802

Max Act: 5.0427. Min Act: -0.1700

Data Index: 1556072 (Python Code)

Max Activating Token Index: 891

Text #12

Max Range: 5.4802. Min Range: -5.4802

Max Act: 5.0740. Min Act: -0.1700

Data Index: 1419017 (Python Code)

Max Activating Token Index: 169

Text #13

Max Range: 5.4802. Min Range: -5.4802

Max Act: 5.1052. Min Act: -0.1700

Data Index: 1576730 (Python Code)

Max Activating Token Index: 657

Text #14

Max Range: 5.4802. Min Range: -5.4802

Max Act: 5.0427. Min Act: -0.1700

Data Index: 1556872 (Python Code)

Max Activating Token Index: 142

Text #15

Max Range: 5.4802. Min Range: -5.4802

Max Act: 5.0427. Min Act: -0.1700

Data Index: 1375001 (Python Code)

Max Activating Token Index: 232

Text #16

Max Range: 5.4802. Min Range: -5.4802

Max Act: 5.0115. Min Act: -0.1700

Data Index: 1539149 (Python Code)

Max Activating Token Index: 633

Text #17

Max Range: 5.4802. Min Range: -5.4802

Max Act: 5.0115. Min Act: -0.1700

Data Index: 1525278 (Python Code)

Max Activating Token Index: 69

Text #18

Max Range: 5.4802. Min Range: -5.4802

Max Act: 5.0115. Min Act: -0.1700

Data Index: 1452131 (Python Code)

Max Activating Token Index: 91

Text #19

Max Range: 5.4802. Min Range: -5.4802

Max Act: 4.9490. Min Act: -0.1700

Data Index: 1569193 (Python Code)

Max Activating Token Index: 166