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

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

Neuron 1332 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.8120. Min Act: -0.1700

Data Index: 1220819 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.8120. Min Act: -0.1700

Data Index: 415553 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.5308. Min Act: -0.1700

Data Index: 1114792 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.5308. Min Act: -0.1700

Data Index: 965006 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.4995. Min Act: -0.1700

Data Index: 1153433 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.4995. Min Act: -0.1700

Data Index: 593697 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.5308. Min Act: -0.1700

Data Index: 1199150 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.4370. Min Act: -0.1700

Data Index: 832374 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.4683. Min Act: -0.1700

Data Index: 57925 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.3745. Min Act: -0.1700

Data Index: 357964 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.4370. Min Act: -0.1700

Data Index: 1233041 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.3433. Min Act: -0.1700

Data Index: 97136 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.3433. Min Act: -0.1700

Data Index: 1124416 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.3745. Min Act: -0.1700

Data Index: 996332 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.3745. Min Act: -0.1700

Data Index: 1207512 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.3433. Min Act: -0.1700

Data Index: 66922 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.2808. Min Act: -0.1700

Data Index: 304304 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.3120. Min Act: -0.1700

Data Index: 263058 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.3433. Min Act: -0.1700

Data Index: 619698 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 5.8120. Min Range: -5.8120

Max Act: 5.2808. Min Act: -0.1700

Data Index: 1171407 (C4 (Web Text))

Max Activating Token Index: 911