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

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

Neuron 399 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: 5.9173. Min Range: -5.9173

Max Act: 5.9173. Min Act: -0.1700

Data Index: 900789 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 5.9173. Min Range: -5.9173

Max Act: 5.7298. Min Act: -0.1700

Data Index: 1261202 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 5.9173. Min Range: -5.9173

Max Act: 5.6986. Min Act: -0.1700

Data Index: 89039 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 5.9173. Min Range: -5.9173

Max Act: 5.6361. Min Act: -0.1700

Data Index: 1179380 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 5.9173. Min Range: -5.9173

Max Act: 5.6361. Min Act: -0.1700

Data Index: 1228100 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 5.9173. Min Range: -5.9173

Max Act: 5.5423. Min Act: -0.1700

Data Index: 650557 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 5.9173. Min Range: -5.9173

Max Act: 5.6048. Min Act: -0.1700

Data Index: 1171208 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 5.9173. Min Range: -5.9173

Max Act: 5.5736. Min Act: -0.1700

Data Index: 751730 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 5.9173. Min Range: -5.9173

Max Act: 5.6048. Min Act: -0.1700

Data Index: 739155 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 5.9173. Min Range: -5.9173

Max Act: 5.5736. Min Act: -0.1700

Data Index: 412964 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 5.9173. Min Range: -5.9173

Max Act: 5.6048. Min Act: -0.1700

Data Index: 151460 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 5.9173. Min Range: -5.9173

Max Act: 5.5423. Min Act: -0.1700

Data Index: 15499 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 5.9173. Min Range: -5.9173

Max Act: 5.5736. Min Act: -0.1700

Data Index: 1158206 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 5.9173. Min Range: -5.9173

Max Act: 5.5111. Min Act: -0.1700

Data Index: 87306 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 5.9173. Min Range: -5.9173

Max Act: 5.5111. Min Act: -0.1700

Data Index: 328327 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 5.9173. Min Range: -5.9173

Max Act: 5.5423. Min Act: -0.1700

Data Index: 115500 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 5.9173. Min Range: -5.9173

Max Act: 5.5111. Min Act: -0.1700

Data Index: 145549 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 5.9173. Min Range: -5.9173

Max Act: 5.4798. Min Act: -0.1700

Data Index: 1318719 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 5.9173. Min Range: -5.9173

Max Act: 5.5111. Min Act: -0.1700

Data Index: 368608 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 5.9173. Min Range: -5.9173

Max Act: 5.4798. Min Act: -0.1700

Data Index: 718014 (C4 (Web Text))

Max Activating Token Index: 464