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

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

Neuron 1007 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: 3.6157. Min Range: -3.6157

Max Act: 3.6157. Min Act: -0.1700

Data Index: 764360 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.3964. Min Act: -0.1700

Data Index: 1645749 (Python Code)

Max Activating Token Index: 891

Text #2

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.3493. Min Act: -0.1700

Data Index: 378740 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.2708. Min Act: -0.1700

Data Index: 751424 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.2865. Min Act: -0.1700

Data Index: 749790 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.3022. Min Act: -0.1700

Data Index: 414976 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.3022. Min Act: -0.1700

Data Index: 350855 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.2708. Min Act: -0.1700

Data Index: 232651 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.2551. Min Act: -0.1700

Data Index: 216437 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.2708. Min Act: -0.1700

Data Index: 1105722 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.2708. Min Act: -0.1700

Data Index: 706291 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.2393. Min Act: -0.1700

Data Index: 969419 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.2393. Min Act: -0.1700

Data Index: 919854 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.2551. Min Act: -0.1700

Data Index: 677764 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.2393. Min Act: -0.1700

Data Index: 1281052 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.2393. Min Act: -0.1700

Data Index: 1278665 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.2236. Min Act: -0.1700

Data Index: 907655 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.2393. Min Act: -0.1700

Data Index: 999941 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.2393. Min Act: -0.1700

Data Index: 1079581 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.2393. Min Act: -0.1700

Data Index: 155392 (C4 (Web Text))

Max Activating Token Index: 124