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

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

Neuron 1628 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.5003. Min Act: -0.1700

Data Index: 1164765 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4689. Min Act: -0.1700

Data Index: 1217720 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4846. Min Act: -0.1700

Data Index: 269907 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4376. Min Act: -0.1700

Data Index: 372077 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4219. Min Act: -0.1700

Data Index: 833388 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4689. Min Act: -0.1700

Data Index: 444298 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4376. Min Act: -0.1700

Data Index: 1168106 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4219. Min Act: -0.1700

Data Index: 410466 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4376. Min Act: -0.1700

Data Index: 424213 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4219. Min Act: -0.1700

Data Index: 458292 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.3748. Min Act: -0.1700

Data Index: 684490 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.3121. Min Act: -0.1700

Data Index: 159189 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.3435. Min Act: -0.1700

Data Index: 80718 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4062. Min Act: -0.1700

Data Index: 518487 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.3592. Min Act: -0.1700

Data Index: 319586 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.3905. Min Act: -0.1700

Data Index: 304990 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.3435. Min Act: -0.1700

Data Index: 663813 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.3905. Min Act: -0.1700

Data Index: 411870 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4219. Min Act: -0.1700

Data Index: 818041 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.3278. Min Act: -0.1700

Data Index: 614663 (C4 (Web Text))

Max Activating Token Index: 796