Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 153 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.6427. Min Act: -0.1700

Data Index: 657503 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.5802. Min Act: -0.1700

Data Index: 603734 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.6115. Min Act: -0.1700

Data Index: 781055 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.5490. Min Act: -0.1700

Data Index: 118311 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.6115. Min Act: -0.1700

Data Index: 659933 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.4865. Min Act: -0.1700

Data Index: 30467 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.5490. Min Act: -0.1700

Data Index: 1127768 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.4552. Min Act: -0.1700

Data Index: 1129470 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.5177. Min Act: -0.1700

Data Index: 1153138 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.4865. Min Act: -0.1700

Data Index: 1197066 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.4865. Min Act: -0.1700

Data Index: 1019380 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.4865. Min Act: -0.1700

Data Index: 305582 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.4240. Min Act: -0.1700

Data Index: 579049 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.4865. Min Act: -0.1700

Data Index: 1030965 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.5490. Min Act: -0.1700

Data Index: 1344752 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.4240. Min Act: -0.1700

Data Index: 352596 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.3615. Min Act: -0.1700

Data Index: 42241 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.3302. Min Act: -0.1700

Data Index: 160433 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.3927. Min Act: -0.1700

Data Index: 656657 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 5.6427. Min Range: -5.6427

Max Act: 5.4240. Min Act: -0.1700

Data Index: 816909 (C4 (Web Text))

Max Activating Token Index: 344