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

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

Neuron 1814 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.8547. Min Act: -0.1700

Data Index: 108534 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.8376. Min Act: -0.1700

Data Index: 542693 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.8462. Min Act: -0.1700

Data Index: 308232 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.8290. Min Act: -0.1700

Data Index: 473648 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.8290. Min Act: -0.1700

Data Index: 310159 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.8290. Min Act: -0.1700

Data Index: 537205 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.8119. Min Act: -0.1700

Data Index: 947042 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.8462. Min Act: -0.1700

Data Index: 488800 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.8033. Min Act: -0.1700

Data Index: 1427153 (Python Code)

Max Activating Token Index: 294

Text #9

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.8119. Min Act: -0.1700

Data Index: 536772 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.8033. Min Act: -0.1700

Data Index: 723356 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.8033. Min Act: -0.1700

Data Index: 1079897 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.8033. Min Act: -0.1700

Data Index: 473527 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.7861. Min Act: -0.1700

Data Index: 714677 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.7947. Min Act: -0.1700

Data Index: 1034683 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.7861. Min Act: -0.1700

Data Index: 801333 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.7861. Min Act: -0.1700

Data Index: 275680 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.7861. Min Act: -0.1700

Data Index: 1304705 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.7775. Min Act: -0.1700

Data Index: 899930 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.7861. Min Act: -0.1700

Data Index: 602851 (C4 (Web Text))

Max Activating Token Index: 870