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

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

Neuron 1917 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.4924. Min Act: -0.1700

Data Index: 1317570 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.1469. Min Act: -0.1700

Data Index: 1226396 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.1154. Min Act: -0.1700

Data Index: 734530 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.0996. Min Act: -0.1700

Data Index: 483458 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.1311. Min Act: -0.1700

Data Index: 157724 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.1154. Min Act: -0.1700

Data Index: 210502 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.0839. Min Act: -0.1700

Data Index: 1019019 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.0839. Min Act: -0.1700

Data Index: 633717 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.0523. Min Act: -0.1700

Data Index: 565891 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.0839. Min Act: -0.1700

Data Index: 155036 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.0523. Min Act: -0.1700

Data Index: 1272033 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.0049. Min Act: -0.1700

Data Index: 38 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.0523. Min Act: -0.1700

Data Index: 128921 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.0207. Min Act: -0.1700

Data Index: 393940 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.0365. Min Act: -0.1700

Data Index: 956220 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 3.4924. Min Range: -3.4924

Max Act: 2.9891. Min Act: -0.1700

Data Index: 692613 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.0207. Min Act: -0.1700

Data Index: 1326344 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.0207. Min Act: -0.1700

Data Index: 736450 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.0207. Min Act: -0.1700

Data Index: 1099982 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.0049. Min Act: -0.1700

Data Index: 840501 (C4 (Web Text))

Max Activating Token Index: 158