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

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

Neuron 1085 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.7383. Min Act: -0.1700

Data Index: 584201 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.7070. Min Act: -0.1700

Data Index: 31365 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.6444. Min Act: -0.1700

Data Index: 1342580 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.7070. Min Act: -0.1700

Data Index: 1081661 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.7070. Min Act: -0.1700

Data Index: 789794 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.7070. Min Act: -0.1700

Data Index: 570000 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.6444. Min Act: -0.1700

Data Index: 463034 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.5505. Min Act: -0.1700

Data Index: 1283804 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.5818. Min Act: -0.1700

Data Index: 1295060 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.5505. Min Act: -0.1700

Data Index: 360841 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.6131. Min Act: -0.1700

Data Index: 546999 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.5818. Min Act: -0.1700

Data Index: 432349 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.5818. Min Act: -0.1700

Data Index: 881352 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.5818. Min Act: -0.1700

Data Index: 550299 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.5818. Min Act: -0.1700

Data Index: 310476 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.5505. Min Act: -0.1700

Data Index: 1238326 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.5505. Min Act: -0.1700

Data Index: 435416 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.5818. Min Act: -0.1700

Data Index: 544425 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.4564. Min Act: -0.1700

Data Index: 627541 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 3.7383. Min Range: -3.7383

Max Act: 3.5505. Min Act: -0.1700

Data Index: 847680 (C4 (Web Text))

Max Activating Token Index: 87