Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 987 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.9304. Min Act: -0.1700

Data Index: 1220576 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.8366. Min Act: -0.1700

Data Index: 76824 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.6802. Min Act: -0.1700

Data Index: 14669 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.6176. Min Act: -0.1700

Data Index: 573045 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.6176. Min Act: -0.1700

Data Index: 642045 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.5862. Min Act: -0.1700

Data Index: 111897 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.5862. Min Act: -0.1700

Data Index: 1022496 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.5236. Min Act: -0.1700

Data Index: 465267 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.5079. Min Act: -0.1700

Data Index: 215890 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.5393. Min Act: -0.1700

Data Index: 266599 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.5393. Min Act: -0.1700

Data Index: 690707 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.4923. Min Act: -0.1700

Data Index: 976870 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.4923. Min Act: -0.1700

Data Index: 53695 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.4766. Min Act: -0.1700

Data Index: 1285181 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.5393. Min Act: -0.1700

Data Index: 1118646 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.5236. Min Act: -0.1700

Data Index: 1018011 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.4923. Min Act: -0.1700

Data Index: 248399 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.4923. Min Act: -0.1700

Data Index: 307683 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.4923. Min Act: -0.1700

Data Index: 357956 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 3.9304. Min Range: -3.9304

Max Act: 3.5079. Min Act: -0.1700

Data Index: 662168 (C4 (Web Text))

Max Activating Token Index: 660