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

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

Neuron 1414 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: 3.7799. Min Range: -3.7799

Max Act: 3.7799. Min Act: -0.1700

Data Index: 1235435 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.7330. Min Act: -0.1700

Data Index: 504134 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.7173. Min Act: -0.1700

Data Index: 1048203 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.6860. Min Act: -0.1700

Data Index: 958910 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.6547. Min Act: -0.1700

Data Index: 827410 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.6391. Min Act: -0.1700

Data Index: 960417 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.5921. Min Act: -0.1700

Data Index: 182080 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.6234. Min Act: -0.1700

Data Index: 634275 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.5921. Min Act: -0.1700

Data Index: 11418 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.6391. Min Act: -0.1699

Data Index: 532447 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.5921. Min Act: -0.1700

Data Index: 310514 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.5608. Min Act: -0.1700

Data Index: 1176054 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.5921. Min Act: -0.1700

Data Index: 238863 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.5451. Min Act: -0.1700

Data Index: 448696 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.5608. Min Act: -0.1700

Data Index: 628705 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.5764. Min Act: -0.1700

Data Index: 552452 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.5764. Min Act: -0.1700

Data Index: 37523 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.5451. Min Act: -0.1700

Data Index: 518093 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.5295. Min Act: -0.1700

Data Index: 709876 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 3.7799. Min Range: -3.7799

Max Act: 3.5138. Min Act: -0.1700

Data Index: 165729 (C4 (Web Text))

Max Activating Token Index: 159