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

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

Neuron 676 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: 3.7864. Min Range: -3.7864

Max Act: 3.7864. Min Act: -0.1700

Data Index: 1118733 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 3.7864. Min Range: -3.7864

Max Act: 3.7864. Min Act: -0.1700

Data Index: 807130 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 3.7864. Min Range: -3.7864

Max Act: 3.7552. Min Act: -0.1700

Data Index: 291354 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 3.7864. Min Range: -3.7864

Max Act: 3.7239. Min Act: -0.1700

Data Index: 1296625 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 3.7864. Min Range: -3.7864

Max Act: 3.7552. Min Act: -0.1700

Data Index: 392431 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 3.7864. Min Range: -3.7864

Max Act: 3.6926. Min Act: -0.1700

Data Index: 1107898 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 3.7864. Min Range: -3.7864

Max Act: 3.6926. Min Act: -0.1700

Data Index: 936950 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 3.7864. Min Range: -3.7864

Max Act: 3.6300. Min Act: -0.1700

Data Index: 968387 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 3.7864. Min Range: -3.7864

Max Act: 3.6613. Min Act: -0.1700

Data Index: 398485 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 3.7864. Min Range: -3.7864

Max Act: 3.6613. Min Act: -0.1700

Data Index: 303002 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 3.7864. Min Range: -3.7864

Max Act: 3.6926. Min Act: -0.1700

Data Index: 570043 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 3.7864. Min Range: -3.7864

Max Act: 3.6613. Min Act: -0.1700

Data Index: 1078072 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 3.7864. Min Range: -3.7864

Max Act: 3.6300. Min Act: -0.1700

Data Index: 1323500 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 3.7864. Min Range: -3.7864

Max Act: 3.5987. Min Act: -0.1700

Data Index: 804358 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 3.7864. Min Range: -3.7864

Max Act: 3.6300. Min Act: -0.1700

Data Index: 1220336 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 3.7864. Min Range: -3.7864

Max Act: 3.6300. Min Act: -0.1700

Data Index: 988331 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 3.7864. Min Range: -3.7864

Max Act: 3.5987. Min Act: -0.1700

Data Index: 451133 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 3.7864. Min Range: -3.7864

Max Act: 3.5987. Min Act: -0.1700

Data Index: 131961 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 3.7864. Min Range: -3.7864

Max Act: 3.5047. Min Act: -0.1700

Data Index: 547131 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 3.7864. Min Range: -3.7864

Max Act: 3.5673. Min Act: -0.1700

Data Index: 342022 (C4 (Web Text))

Max Activating Token Index: 263