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

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

Neuron 357 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: 3.7806. Min Range: -3.7806

Max Act: 3.7806. Min Act: -0.1700

Data Index: 215111 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 3.7806. Min Range: -3.7806

Max Act: 3.7180. Min Act: -0.1700

Data Index: 885834 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 3.7806. Min Range: -3.7806

Max Act: 3.6867. Min Act: -0.1700

Data Index: 1207607 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 3.7806. Min Range: -3.7806

Max Act: 3.6867. Min Act: -0.1700

Data Index: 33707 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 3.7806. Min Range: -3.7806

Max Act: 3.6867. Min Act: -0.1700

Data Index: 1106081 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 3.7806. Min Range: -3.7806

Max Act: 3.6867. Min Act: -0.1700

Data Index: 576810 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 3.7806. Min Range: -3.7806

Max Act: 3.6867. Min Act: -0.1700

Data Index: 332820 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 3.7806. Min Range: -3.7806

Max Act: 3.6554. Min Act: -0.1700

Data Index: 126427 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 3.7806. Min Range: -3.7806

Max Act: 3.6554. Min Act: -0.1700

Data Index: 434876 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 3.7806. Min Range: -3.7806

Max Act: 3.6241. Min Act: -0.1700

Data Index: 832644 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 3.7806. Min Range: -3.7806

Max Act: 3.6241. Min Act: -0.1700

Data Index: 59468 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 3.7806. Min Range: -3.7806

Max Act: 3.6241. Min Act: -0.1700

Data Index: 849702 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 3.7806. Min Range: -3.7806

Max Act: 3.6241. Min Act: -0.1700

Data Index: 1107122 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 3.7806. Min Range: -3.7806

Max Act: 3.6554. Min Act: -0.1700

Data Index: 841483 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 3.7806. Min Range: -3.7806

Max Act: 3.6241. Min Act: -0.1700

Data Index: 980369 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 3.7806. Min Range: -3.7806

Max Act: 3.6241. Min Act: -0.1700

Data Index: 1048189 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 3.7806. Min Range: -3.7806

Max Act: 3.6241. Min Act: -0.1700

Data Index: 251529 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 3.7806. Min Range: -3.7806

Max Act: 3.6241. Min Act: -0.1700

Data Index: 409837 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 3.7806. Min Range: -3.7806

Max Act: 3.6241. Min Act: -0.1700

Data Index: 677893 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 3.7806. Min Range: -3.7806

Max Act: 3.6241. Min Act: -0.1700

Data Index: 1077545 (C4 (Web Text))

Max Activating Token Index: 763