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

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

Neuron 336 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1073. Min Range: -5.1073

Max Act: 5.1073. Min Act: -0.1700

Data Index: 402793 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 5.1073. Min Range: -5.1073

Max Act: 5.0448. Min Act: -0.1700

Data Index: 708272 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.9823. Min Act: -0.1700

Data Index: 534166 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 5.1073. Min Range: -5.1073

Max Act: 5.0135. Min Act: -0.1700

Data Index: 799042 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 5.1073. Min Range: -5.1073

Max Act: 5.0135. Min Act: -0.1700

Data Index: 1240908 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.9198. Min Act: -0.1700

Data Index: 1015978 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 5.1073. Min Range: -5.1073

Max Act: 5.0135. Min Act: -0.1700

Data Index: 773338 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.8885. Min Act: -0.1700

Data Index: 839508 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.9198. Min Act: -0.1700

Data Index: 794379 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.9198. Min Act: -0.1700

Data Index: 1234939 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.9510. Min Act: -0.1700

Data Index: 553802 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.8885. Min Act: -0.1700

Data Index: 782979 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.8885. Min Act: -0.1700

Data Index: 637338 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.8260. Min Act: -0.1700

Data Index: 1019700 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.8573. Min Act: -0.1700

Data Index: 175936 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.8573. Min Act: -0.1700

Data Index: 1242371 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.7948. Min Act: -0.1700

Data Index: 643835 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.8260. Min Act: -0.1700

Data Index: 1282334 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.7635. Min Act: -0.1700

Data Index: 1185742 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.7948. Min Act: -0.1700

Data Index: 442885 (C4 (Web Text))

Max Activating Token Index: 865