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

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

Neuron 1988 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: 5.1801. Min Range: -5.1801

Max Act: 5.1176. Min Act: -0.1700

Data Index: 608054 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 5.1801. Min Range: -5.1801

Max Act: 5.0551. Min Act: -0.1700

Data Index: 36043 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 5.1801. Min Range: -5.1801

Max Act: 5.1801. Min Act: -0.1700

Data Index: 837833 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 5.1801. Min Range: -5.1801

Max Act: 5.0238. Min Act: -0.1700

Data Index: 688589 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 5.1801. Min Range: -5.1801

Max Act: 5.1176. Min Act: -0.1700

Data Index: 1267330 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 5.1801. Min Range: -5.1801

Max Act: 5.0238. Min Act: -0.1700

Data Index: 80260 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 5.1801. Min Range: -5.1801

Max Act: 4.9613. Min Act: -0.1700

Data Index: 327122 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 5.1801. Min Range: -5.1801

Max Act: 5.0863. Min Act: -0.1700

Data Index: 1353554 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 5.1801. Min Range: -5.1801

Max Act: 5.0238. Min Act: -0.1700

Data Index: 845136 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 5.1801. Min Range: -5.1801

Max Act: 5.0238. Min Act: -0.1700

Data Index: 438173 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 5.1801. Min Range: -5.1801

Max Act: 4.9926. Min Act: -0.1700

Data Index: 411944 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 5.1801. Min Range: -5.1801

Max Act: 4.8988. Min Act: -0.1700

Data Index: 515286 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 5.1801. Min Range: -5.1801

Max Act: 4.8988. Min Act: -0.1700

Data Index: 550054 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 5.1801. Min Range: -5.1801

Max Act: 4.8676. Min Act: -0.1700

Data Index: 358998 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 5.1801. Min Range: -5.1801

Max Act: 4.9301. Min Act: -0.1700

Data Index: 1188364 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 5.1801. Min Range: -5.1801

Max Act: 4.8988. Min Act: -0.1700

Data Index: 207867 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 5.1801. Min Range: -5.1801

Max Act: 4.8676. Min Act: -0.1700

Data Index: 465242 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 5.1801. Min Range: -5.1801

Max Act: 4.8363. Min Act: -0.1700

Data Index: 21727 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 5.1801. Min Range: -5.1801

Max Act: 4.8051. Min Act: -0.1700

Data Index: 669153 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 5.1801. Min Range: -5.1801

Max Act: 4.8363. Min Act: -0.1700

Data Index: 986312 (C4 (Web Text))

Max Activating Token Index: 438