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

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

Neuron 423 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: 5.5270. Min Range: -5.5270

Max Act: 5.5270. Min Act: -0.1700

Data Index: 1335177 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 5.5270. Min Range: -5.5270

Max Act: 5.4333. Min Act: -0.1700

Data Index: 628470 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 5.5270. Min Range: -5.5270

Max Act: 5.4333. Min Act: -0.1700

Data Index: 741919 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 5.5270. Min Range: -5.5270

Max Act: 5.4020. Min Act: -0.1700

Data Index: 1311266 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 5.5270. Min Range: -5.5270

Max Act: 5.3708. Min Act: -0.1700

Data Index: 404299 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 5.5270. Min Range: -5.5270

Max Act: 5.3395. Min Act: -0.1700

Data Index: 393912 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 5.5270. Min Range: -5.5270

Max Act: 5.3708. Min Act: -0.1700

Data Index: 323495 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 5.5270. Min Range: -5.5270

Max Act: 5.4020. Min Act: -0.1700

Data Index: 788553 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 5.5270. Min Range: -5.5270

Max Act: 5.3708. Min Act: -0.1700

Data Index: 706389 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 5.5270. Min Range: -5.5270

Max Act: 5.4020. Min Act: -0.1700

Data Index: 937136 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 5.5270. Min Range: -5.5270

Max Act: 5.3395. Min Act: -0.1700

Data Index: 1354662 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 5.5270. Min Range: -5.5270

Max Act: 5.3395. Min Act: -0.1700

Data Index: 881201 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 5.5270. Min Range: -5.5270

Max Act: 5.3083. Min Act: -0.1700

Data Index: 761628 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 5.5270. Min Range: -5.5270

Max Act: 5.3395. Min Act: -0.1700

Data Index: 1333137 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 5.5270. Min Range: -5.5270

Max Act: 5.3083. Min Act: -0.1700

Data Index: 64818 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 5.5270. Min Range: -5.5270

Max Act: 5.2770. Min Act: -0.1700

Data Index: 1278969 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 5.5270. Min Range: -5.5270

Max Act: 5.2458. Min Act: -0.1700

Data Index: 1226727 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 5.5270. Min Range: -5.5270

Max Act: 5.3083. Min Act: -0.1700

Data Index: 400263 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 5.5270. Min Range: -5.5270

Max Act: 5.2770. Min Act: -0.1700

Data Index: 266110 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 5.5270. Min Range: -5.5270

Max Act: 5.2458. Min Act: -0.1700

Data Index: 936364 (C4 (Web Text))

Max Activating Token Index: 597