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

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

Neuron 1811 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: 3.6077. Min Range: -3.6077

Max Act: 3.6077. Min Act: -0.1700

Data Index: 441351 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 3.6077. Min Range: -3.6077

Max Act: 3.5294. Min Act: -0.1700

Data Index: 1247318 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 3.6077. Min Range: -3.6077

Max Act: 3.4980. Min Act: -0.1700

Data Index: 348334 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 3.6077. Min Range: -3.6077

Max Act: 3.4980. Min Act: -0.1700

Data Index: 624422 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 3.6077. Min Range: -3.6077

Max Act: 3.4824. Min Act: -0.1700

Data Index: 1291818 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 3.6077. Min Range: -3.6077

Max Act: 3.4824. Min Act: -0.1700

Data Index: 361182 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 3.6077. Min Range: -3.6077

Max Act: 3.4824. Min Act: -0.1700

Data Index: 1241733 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 3.6077. Min Range: -3.6077

Max Act: 3.4980. Min Act: -0.1700

Data Index: 155154 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 3.6077. Min Range: -3.6077

Max Act: 3.4824. Min Act: -0.1700

Data Index: 626114 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 3.6077. Min Range: -3.6077

Max Act: 3.4824. Min Act: -0.1700

Data Index: 873634 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 3.6077. Min Range: -3.6077

Max Act: 3.4667. Min Act: -0.1700

Data Index: 364541 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 3.6077. Min Range: -3.6077

Max Act: 3.4667. Min Act: -0.1700

Data Index: 725182 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 3.6077. Min Range: -3.6077

Max Act: 3.4667. Min Act: -0.1700

Data Index: 8307 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 3.6077. Min Range: -3.6077

Max Act: 3.4510. Min Act: -0.1700

Data Index: 768842 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 3.6077. Min Range: -3.6077

Max Act: 3.4667. Min Act: -0.1700

Data Index: 371223 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 3.6077. Min Range: -3.6077

Max Act: 3.4510. Min Act: -0.1700

Data Index: 816893 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 3.6077. Min Range: -3.6077

Max Act: 3.4667. Min Act: -0.1700

Data Index: 396281 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 3.6077. Min Range: -3.6077

Max Act: 3.4510. Min Act: -0.1700

Data Index: 873069 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 3.6077. Min Range: -3.6077

Max Act: 3.4667. Min Act: -0.1700

Data Index: 1175158 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 3.6077. Min Range: -3.6077

Max Act: 3.4667. Min Act: -0.1700

Data Index: 316656 (C4 (Web Text))

Max Activating Token Index: 475