Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 82 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.0145. Min Range: -4.0145

Max Act: 4.0145. Min Act: -0.1691

Data Index: 1504634 (Python Code)

Max Activating Token Index: 331

Text #1

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.8269. Min Act: -0.1700

Data Index: 1450561 (Python Code)

Max Activating Token Index: 306

Text #2

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.8425. Min Act: -0.1700

Data Index: 1488389 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.7956. Min Act: -0.1700

Data Index: 1619710 (Python Code)

Max Activating Token Index: 199

Text #4

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.7800. Min Act: -0.1700

Data Index: 1618213 (Python Code)

Max Activating Token Index: 908

Text #5

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.7643. Min Act: -0.1698

Data Index: 1528838 (Python Code)

Max Activating Token Index: 701

Text #6

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.7487. Min Act: -0.1695

Data Index: 1654804 (Python Code)

Max Activating Token Index: 624

Text #7

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.7643. Min Act: -0.1700

Data Index: 1408534 (Python Code)

Max Activating Token Index: 323

Text #8

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.7017. Min Act: -0.1700

Data Index: 1276575 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.7017. Min Act: -0.1700

Data Index: 1617572 (Python Code)

Max Activating Token Index: 645

Text #10

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.7017. Min Act: -0.1700

Data Index: 1422510 (Python Code)

Max Activating Token Index: 818

Text #11

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.7174. Min Act: -0.1700

Data Index: 1434295 (Python Code)

Max Activating Token Index: 62

Text #12

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.7174. Min Act: -0.1700

Data Index: 1531767 (Python Code)

Max Activating Token Index: 782

Text #13

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.7017. Min Act: -0.1699

Data Index: 1438900 (Python Code)

Max Activating Token Index: 166

Text #14

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.7017. Min Act: -0.1700

Data Index: 1613581 (Python Code)

Max Activating Token Index: 1015

Text #15

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.6704. Min Act: -0.1700

Data Index: 1606981 (Python Code)

Max Activating Token Index: 965

Text #16

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.7017. Min Act: -0.1700

Data Index: 1451715 (Python Code)

Max Activating Token Index: 821

Text #17

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.6704. Min Act: -0.1700

Data Index: 1388014 (Python Code)

Max Activating Token Index: 415

Text #18

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.6861. Min Act: -0.1700

Data Index: 1111755 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.6548. Min Act: -0.1700

Data Index: 1599196 (Python Code)

Max Activating Token Index: 537