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

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

Neuron 1769 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: 3.7358. Min Range: -3.7358

Max Act: 3.7358. Min Act: -0.1700

Data Index: 211904 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 3.7358. Min Range: -3.7358

Max Act: 3.6106. Min Act: -0.1700

Data Index: 1035313 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 3.7358. Min Range: -3.7358

Max Act: 3.5793. Min Act: -0.1700

Data Index: 67667 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 3.7358. Min Range: -3.7358

Max Act: 3.5166. Min Act: -0.1700

Data Index: 562812 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 3.7358. Min Range: -3.7358

Max Act: 3.5166. Min Act: -0.1700

Data Index: 1331943 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 3.7358. Min Range: -3.7358

Max Act: 3.5793. Min Act: -0.1700

Data Index: 1331152 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 3.7358. Min Range: -3.7358

Max Act: 3.4226. Min Act: -0.1700

Data Index: 1103271 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 3.7358. Min Range: -3.7358

Max Act: 3.4226. Min Act: -0.1699

Data Index: 1413869 (Python Code)

Max Activating Token Index: 701

Text #8

Max Range: 3.7358. Min Range: -3.7358

Max Act: 3.4853. Min Act: -0.1700

Data Index: 662288 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 3.7358. Min Range: -3.7358

Max Act: 3.5166. Min Act: -0.1700

Data Index: 476813 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 3.7358. Min Range: -3.7358

Max Act: 3.5166. Min Act: -0.1700

Data Index: 800353 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 3.7358. Min Range: -3.7358

Max Act: 3.5166. Min Act: -0.1700

Data Index: 684129 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 3.7358. Min Range: -3.7358

Max Act: 3.5166. Min Act: -0.1700

Data Index: 626509 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 3.7358. Min Range: -3.7358

Max Act: 3.4853. Min Act: -0.1700

Data Index: 1000250 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 3.7358. Min Range: -3.7358

Max Act: 3.4226. Min Act: -0.1700

Data Index: 129771 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 3.7358. Min Range: -3.7358

Max Act: 3.4539. Min Act: -0.1700

Data Index: 479267 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 3.7358. Min Range: -3.7358

Max Act: 3.4853. Min Act: -0.1700

Data Index: 1068394 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 3.7358. Min Range: -3.7358

Max Act: 3.4226. Min Act: -0.1700

Data Index: 1243074 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 3.7358. Min Range: -3.7358

Max Act: 3.4226. Min Act: -0.1700

Data Index: 1459027 (Python Code)

Max Activating Token Index: 1019

Text #19

Max Range: 3.7358. Min Range: -3.7358

Max Act: 3.3912. Min Act: -0.1700

Data Index: 990888 (C4 (Web Text))

Max Activating Token Index: 772