Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1161 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.6562. Min Act: -0.1700

Data Index: 261700 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.5623. Min Act: -0.1700

Data Index: 1053049 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.5936. Min Act: -0.1700

Data Index: 1227909 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.5623. Min Act: -0.1700

Data Index: 1535902 (Python Code)

Max Activating Token Index: 149

Text #4

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.5623. Min Act: -0.1700

Data Index: 1623301 (Python Code)

Max Activating Token Index: 528

Text #5

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.4840. Min Act: -0.1700

Data Index: 1293768 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.4996. Min Act: -0.1700

Data Index: 911380 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.4996. Min Act: -0.1700

Data Index: 836393 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.4683. Min Act: -0.1700

Data Index: 729892 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.4213. Min Act: -0.1700

Data Index: 1412423 (Python Code)

Max Activating Token Index: 976

Text #10

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.4056. Min Act: -0.1700

Data Index: 1581485 (Python Code)

Max Activating Token Index: 37

Text #11

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.4056. Min Act: -0.1700

Data Index: 1121876 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.3899. Min Act: -0.1700

Data Index: 725778 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.3742. Min Act: -0.1700

Data Index: 1550083 (Python Code)

Max Activating Token Index: 98

Text #14

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.3742. Min Act: -0.1700

Data Index: 1164534 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.3428. Min Act: -0.1700

Data Index: 726078 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.3585. Min Act: -0.1700

Data Index: 687387 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.3585. Min Act: -0.1700

Data Index: 1006383 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.3585. Min Act: -0.1700

Data Index: 383501 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 3.6562. Min Range: -3.6562

Max Act: 3.3742. Min Act: -0.1700

Data Index: 688302 (C4 (Web Text))

Max Activating Token Index: 902