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

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

Neuron 1107 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: 5.1254. Min Range: -5.1254

Max Act: 5.1254. Min Act: -0.1700

Data Index: 2199 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 5.1254. Min Range: -5.1254

Max Act: 5.0942. Min Act: -0.1700

Data Index: 520816 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 5.1254. Min Range: -5.1254

Max Act: 5.0942. Min Act: -0.1700

Data Index: 48736 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 5.1254. Min Range: -5.1254

Max Act: 5.0317. Min Act: -0.1700

Data Index: 438819 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 5.1254. Min Range: -5.1254

Max Act: 5.0004. Min Act: -0.1700

Data Index: 620448 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 5.1254. Min Range: -5.1254

Max Act: 5.0317. Min Act: -0.1700

Data Index: 335574 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 5.1254. Min Range: -5.1254

Max Act: 5.0317. Min Act: -0.1700

Data Index: 825014 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 5.1254. Min Range: -5.1254

Max Act: 5.0004. Min Act: -0.1700

Data Index: 859715 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 5.1254. Min Range: -5.1254

Max Act: 5.0317. Min Act: -0.1700

Data Index: 230381 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 5.1254. Min Range: -5.1254

Max Act: 5.0004. Min Act: -0.1700

Data Index: 102531 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 5.1254. Min Range: -5.1254

Max Act: 5.0004. Min Act: -0.1700

Data Index: 283475 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 5.1254. Min Range: -5.1254

Max Act: 4.9692. Min Act: -0.1700

Data Index: 142604 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 5.1254. Min Range: -5.1254

Max Act: 5.0004. Min Act: -0.1700

Data Index: 430260 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 5.1254. Min Range: -5.1254

Max Act: 4.9692. Min Act: -0.1700

Data Index: 161181 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 5.1254. Min Range: -5.1254

Max Act: 4.9692. Min Act: -0.1700

Data Index: 419582 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 5.1254. Min Range: -5.1254

Max Act: 4.9692. Min Act: -0.1700

Data Index: 384736 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 5.1254. Min Range: -5.1254

Max Act: 4.9692. Min Act: -0.1700

Data Index: 334864 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 5.1254. Min Range: -5.1254

Max Act: 4.9692. Min Act: -0.1700

Data Index: 31159 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 5.1254. Min Range: -5.1254

Max Act: 5.0004. Min Act: -0.1700

Data Index: 546089 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 5.1254. Min Range: -5.1254

Max Act: 5.0004. Min Act: -0.1700

Data Index: 596641 (C4 (Web Text))

Max Activating Token Index: 558