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

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

Neuron 1730 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: 10.7781. Min Range: -10.7781

Max Act: 10.7156. Min Act: -0.1700

Data Index: 314164 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 10.7781. Min Range: -10.7781

Max Act: 10.7781. Min Act: -0.1700

Data Index: 824679 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 10.7781. Min Range: -10.7781

Max Act: 10.5281. Min Act: -0.1700

Data Index: 45750 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 10.7781. Min Range: -10.7781

Max Act: 10.4031. Min Act: -0.1700

Data Index: 1338799 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 10.7781. Min Range: -10.7781

Max Act: 10.4031. Min Act: -0.1699

Data Index: 1205291 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 10.7781. Min Range: -10.7781

Max Act: 10.2156. Min Act: -0.1700

Data Index: 1239410 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 10.7781. Min Range: -10.7781

Max Act: 10.2781. Min Act: -0.1700

Data Index: 1032616 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 10.7781. Min Range: -10.7781

Max Act: 10.1531. Min Act: -0.1700

Data Index: 244919 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 10.7781. Min Range: -10.7781

Max Act: 10.3406. Min Act: -0.1700

Data Index: 600679 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 10.7781. Min Range: -10.7781

Max Act: 10.1531. Min Act: -0.1700

Data Index: 189147 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 10.7781. Min Range: -10.7781

Max Act: 10.0906. Min Act: -0.1700

Data Index: 1158565 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 10.7781. Min Range: -10.7781

Max Act: 9.9656. Min Act: -0.1700

Data Index: 1024089 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 10.7781. Min Range: -10.7781

Max Act: 10.0906. Min Act: -0.1700

Data Index: 652667 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 10.7781. Min Range: -10.7781

Max Act: 10.0906. Min Act: -0.1700

Data Index: 68338 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 10.7781. Min Range: -10.7781

Max Act: 10.0281. Min Act: -0.1700

Data Index: 423777 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 10.7781. Min Range: -10.7781

Max Act: 9.9031. Min Act: -0.1699

Data Index: 1111136 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 10.7781. Min Range: -10.7781

Max Act: 10.0281. Min Act: -0.1700

Data Index: 599460 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 10.7781. Min Range: -10.7781

Max Act: 10.0281. Min Act: -0.1699

Data Index: 753242 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 10.7781. Min Range: -10.7781

Max Act: 10.0281. Min Act: -0.1700

Data Index: 764744 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 10.7781. Min Range: -10.7781

Max Act: 9.9031. Min Act: -0.1700

Data Index: 844636 (C4 (Web Text))

Max Activating Token Index: 274