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

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

Neuron 489 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.3114. Min Act: -0.1700

Data Index: 1303794 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2486. Min Act: -0.1700

Data Index: 1303282 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2171. Min Act: -0.1700

Data Index: 1048204 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2486. Min Act: -0.1700

Data Index: 890742 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.1542. Min Act: -0.1700

Data Index: 572721 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.1542. Min Act: -0.1700

Data Index: 980759 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.1384. Min Act: -0.1700

Data Index: 524035 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.1384. Min Act: -0.1700

Data Index: 860510 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.1069. Min Act: -0.1700

Data Index: 818592 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.1542. Min Act: -0.1700

Data Index: 1118289 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.0912. Min Act: -0.1700

Data Index: 887276 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.0754. Min Act: -0.1700

Data Index: 129840 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.0596. Min Act: -0.1700

Data Index: 1055224 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.0596. Min Act: -0.1700

Data Index: 1331528 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.0438. Min Act: -0.1700

Data Index: 548175 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.0438. Min Act: -0.1700

Data Index: 1159886 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.0280. Min Act: -0.1700

Data Index: 914788 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.0596. Min Act: -0.1700

Data Index: 298038 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.0438. Min Act: -0.1700

Data Index: 1106564 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.0438. Min Act: -0.1700

Data Index: 982061 (C4 (Web Text))

Max Activating Token Index: 603