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

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

Neuron 536 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.3143. Min Act: -0.1700

Data Index: 521601 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.2829. Min Act: -0.1700

Data Index: 853723 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.2515. Min Act: -0.1700

Data Index: 608358 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.2357. Min Act: -0.1700

Data Index: 300171 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.2357. Min Act: -0.1700

Data Index: 180155 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.2043. Min Act: -0.1700

Data Index: 70512 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.2357. Min Act: -0.1700

Data Index: 774580 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.2200. Min Act: -0.1700

Data Index: 1008164 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.2357. Min Act: -0.1700

Data Index: 831874 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.2357. Min Act: -0.1700

Data Index: 135215 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.2357. Min Act: -0.1700

Data Index: 1265716 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.2200. Min Act: -0.1700

Data Index: 933819 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.2200. Min Act: -0.1700

Data Index: 935091 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.2515. Min Act: -0.1700

Data Index: 75156 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.2043. Min Act: -0.1700

Data Index: 653263 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.2200. Min Act: -0.1700

Data Index: 1354635 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.2200. Min Act: -0.1700

Data Index: 457745 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.2200. Min Act: -0.1700

Data Index: 863293 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.2043. Min Act: -0.1700

Data Index: 921265 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.2043. Min Act: -0.1700

Data Index: 546985 (C4 (Web Text))

Max Activating Token Index: 3