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

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

Neuron 616 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.3750. Min Act: -0.1700

Data Index: 1418905 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.3750. Min Act: -0.1700

Data Index: 172738 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.1865. Min Act: -0.1700

Data Index: 1331007 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.2337. Min Act: -0.1700

Data Index: 312809 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.1865. Min Act: -0.1700

Data Index: 837268 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.1708. Min Act: -0.1700

Data Index: 1082425 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.1393. Min Act: -0.1700

Data Index: 696897 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.1865. Min Act: -0.1700

Data Index: 301933 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.1393. Min Act: -0.1700

Data Index: 316106 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.2022. Min Act: -0.1700

Data Index: 1028925 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.1078. Min Act: -0.1700

Data Index: 1010318 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.1235. Min Act: -0.1700

Data Index: 884309 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.1078. Min Act: -0.1699

Data Index: 306854 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.2022. Min Act: -0.1700

Data Index: 17610 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.1235. Min Act: -0.1700

Data Index: 1144072 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.1550. Min Act: -0.1700

Data Index: 527821 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.1078. Min Act: -0.1700

Data Index: 1046920 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.0920. Min Act: -0.1700

Data Index: 1034088 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.1393. Min Act: -0.1700

Data Index: 769950 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.1393. Min Act: -0.1700

Data Index: 383743 (C4 (Web Text))

Max Activating Token Index: 348