Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 688 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.0577. Min Range: -4.0577

Max Act: 4.0577. Min Act: -0.1700

Data Index: 928658 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 4.0577. Min Range: -4.0577

Max Act: 3.9952. Min Act: -0.1700

Data Index: 767208 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 4.0577. Min Range: -4.0577

Max Act: 3.8701. Min Act: -0.1700

Data Index: 911986 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 4.0577. Min Range: -4.0577

Max Act: 3.7137. Min Act: -0.1700

Data Index: 132079 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 4.0577. Min Range: -4.0577

Max Act: 3.6511. Min Act: -0.1700

Data Index: 165417 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 4.0577. Min Range: -4.0577

Max Act: 3.6198. Min Act: -0.1700

Data Index: 1499228 (Python Code)

Max Activating Token Index: 173

Text #6

Max Range: 4.0577. Min Range: -4.0577

Max Act: 3.6511. Min Act: -0.1700

Data Index: 406505 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 4.0577. Min Range: -4.0577

Max Act: 3.5728. Min Act: -0.1700

Data Index: 761868 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 4.0577. Min Range: -4.0577

Max Act: 3.5885. Min Act: -0.1700

Data Index: 270433 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 4.0577. Min Range: -4.0577

Max Act: 3.5728. Min Act: -0.1700

Data Index: 1145758 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 4.0577. Min Range: -4.0577

Max Act: 3.5258. Min Act: -0.1700

Data Index: 1359057 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 4.0577. Min Range: -4.0577

Max Act: 3.5102. Min Act: -0.1700

Data Index: 7873 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 4.0577. Min Range: -4.0577

Max Act: 3.5415. Min Act: -0.1700

Data Index: 1573444 (Python Code)

Max Activating Token Index: 462

Text #13

Max Range: 4.0577. Min Range: -4.0577

Max Act: 3.5102. Min Act: -0.1700

Data Index: 452619 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 4.0577. Min Range: -4.0577

Max Act: 3.5572. Min Act: -0.1700

Data Index: 1281290 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 4.0577. Min Range: -4.0577

Max Act: 3.4945. Min Act: -0.1700

Data Index: 852984 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 4.0577. Min Range: -4.0577

Max Act: 3.4788. Min Act: -0.1700

Data Index: 881899 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 4.0577. Min Range: -4.0577

Max Act: 3.4945. Min Act: -0.1700

Data Index: 1266932 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 4.0577. Min Range: -4.0577

Max Act: 3.4945. Min Act: -0.1700

Data Index: 1407026 (Python Code)

Max Activating Token Index: 740

Text #19

Max Range: 4.0577. Min Range: -4.0577

Max Act: 3.4475. Min Act: -0.1700

Data Index: 445703 (C4 (Web Text))

Max Activating Token Index: 413