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

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

Neuron 1718 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: 5.7144. Min Range: -5.7144

Max Act: 5.7144. Min Act: -0.1700

Data Index: 1240355 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 5.7144. Min Range: -5.7144

Max Act: 5.6519. Min Act: -0.1700

Data Index: 838570 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 5.7144. Min Range: -5.7144

Max Act: 5.6831. Min Act: -0.1700

Data Index: 722559 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 5.7144. Min Range: -5.7144

Max Act: 5.5894. Min Act: -0.1700

Data Index: 8489 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 5.7144. Min Range: -5.7144

Max Act: 5.5581. Min Act: -0.1700

Data Index: 117193 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 5.7144. Min Range: -5.7144

Max Act: 5.3706. Min Act: -0.1700

Data Index: 845326 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 5.7144. Min Range: -5.7144

Max Act: 5.5581. Min Act: -0.1700

Data Index: 81722 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 5.7144. Min Range: -5.7144

Max Act: 5.4019. Min Act: -0.1700

Data Index: 500659 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 5.7144. Min Range: -5.7144

Max Act: 5.5581. Min Act: -0.1700

Data Index: 1154634 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 5.7144. Min Range: -5.7144

Max Act: 5.4019. Min Act: -0.1700

Data Index: 711859 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 5.7144. Min Range: -5.7144

Max Act: 5.5581. Min Act: -0.1700

Data Index: 285775 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 5.7144. Min Range: -5.7144

Max Act: 5.7144. Min Act: -0.1700

Data Index: 1226711 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 5.7144. Min Range: -5.7144

Max Act: 5.4956. Min Act: -0.1700

Data Index: 1172257 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 5.7144. Min Range: -5.7144

Max Act: 5.3706. Min Act: -0.1700

Data Index: 826283 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 5.7144. Min Range: -5.7144

Max Act: 5.2456. Min Act: -0.1700

Data Index: 274753 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 5.7144. Min Range: -5.7144

Max Act: 5.3706. Min Act: -0.1700

Data Index: 1072800 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 5.7144. Min Range: -5.7144

Max Act: 5.4019. Min Act: -0.1700

Data Index: 71825 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 5.7144. Min Range: -5.7144

Max Act: 5.3081. Min Act: -0.1700

Data Index: 1284381 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 5.7144. Min Range: -5.7144

Max Act: 5.3706. Min Act: -0.1700

Data Index: 913312 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 5.7144. Min Range: -5.7144

Max Act: 5.3394. Min Act: -0.1700

Data Index: 809489 (C4 (Web Text))

Max Activating Token Index: 280