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

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

Neuron 1070 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.3837. Min Act: -0.1700

Data Index: 977643 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.3209. Min Act: -0.1700

Data Index: 763230 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.2423. Min Act: -0.1700

Data Index: 424583 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1952. Min Act: -0.1700

Data Index: 497490 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1952. Min Act: -0.1700

Data Index: 222942 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1794. Min Act: -0.1700

Data Index: 863343 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1952. Min Act: -0.1700

Data Index: 246389 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1637. Min Act: -0.1700

Data Index: 639187 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1479. Min Act: -0.1700

Data Index: 665591 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1479. Min Act: -0.1700

Data Index: 908846 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1479. Min Act: -0.1700

Data Index: 705186 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1322. Min Act: -0.1700

Data Index: 861572 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1164. Min Act: -0.1700

Data Index: 1342058 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1322. Min Act: -0.1700

Data Index: 78432 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1007. Min Act: -0.1700

Data Index: 1087901 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.0691. Min Act: -0.1700

Data Index: 304542 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.0533. Min Act: -0.1700

Data Index: 462957 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.0375. Min Act: -0.1700

Data Index: 650856 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.0375. Min Act: -0.1700

Data Index: 1060632 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.0375. Min Act: -0.1700

Data Index: 1337501 (C4 (Web Text))

Max Activating Token Index: 239