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

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

Neuron 1007 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2728. Min Range: -5.2728

Max Act: 5.2728. Min Act: -0.1700

Data Index: 603581 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 5.2728. Min Range: -5.2728

Max Act: 5.2728. Min Act: -0.1700

Data Index: 246522 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 5.2728. Min Range: -5.2728

Max Act: 4.7728. Min Act: -0.1700

Data Index: 511889 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 5.2728. Min Range: -5.2728

Max Act: 4.7416. Min Act: -0.1700

Data Index: 501301 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 5.2728. Min Range: -5.2728

Max Act: 4.7416. Min Act: -0.1700

Data Index: 1216244 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 5.2728. Min Range: -5.2728

Max Act: 4.7103. Min Act: -0.1700

Data Index: 734651 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 5.2728. Min Range: -5.2728

Max Act: 4.7416. Min Act: -0.1700

Data Index: 1325200 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 5.2728. Min Range: -5.2728

Max Act: 4.6791. Min Act: -0.1700

Data Index: 590239 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 5.2728. Min Range: -5.2728

Max Act: 4.7103. Min Act: -0.1700

Data Index: 680872 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 5.2728. Min Range: -5.2728

Max Act: 4.6478. Min Act: -0.1700

Data Index: 1064095 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 5.2728. Min Range: -5.2728

Max Act: 4.6166. Min Act: -0.1700

Data Index: 180434 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 5.2728. Min Range: -5.2728

Max Act: 4.7103. Min Act: -0.1700

Data Index: 746694 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 5.2728. Min Range: -5.2728

Max Act: 4.6791. Min Act: -0.1700

Data Index: 996455 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 5.2728. Min Range: -5.2728

Max Act: 4.6791. Min Act: -0.1700

Data Index: 463041 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 5.2728. Min Range: -5.2728

Max Act: 4.6166. Min Act: -0.1700

Data Index: 1312869 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 5.2728. Min Range: -5.2728

Max Act: 4.6478. Min Act: -0.1700

Data Index: 799474 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 5.2728. Min Range: -5.2728

Max Act: 4.6478. Min Act: -0.1700

Data Index: 1194608 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 5.2728. Min Range: -5.2728

Max Act: 4.5541. Min Act: -0.1700

Data Index: 331052 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 5.2728. Min Range: -5.2728

Max Act: 4.5541. Min Act: -0.1700

Data Index: 939689 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 5.2728. Min Range: -5.2728

Max Act: 4.6166. Min Act: -0.1700

Data Index: 481943 (C4 (Web Text))

Max Activating Token Index: 285