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

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

Neuron 1080 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: 5.3272. Min Range: -5.3272

Max Act: 5.3272. Min Act: -0.1700

Data Index: 591743 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 5.3272. Min Range: -5.3272

Max Act: 4.9834. Min Act: -0.1700

Data Index: 405448 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 5.3272. Min Range: -5.3272

Max Act: 4.9209. Min Act: -0.1700

Data Index: 356798 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 5.3272. Min Range: -5.3272

Max Act: 4.8272. Min Act: -0.1700

Data Index: 240027 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 5.3272. Min Range: -5.3272

Max Act: 4.7959. Min Act: -0.1700

Data Index: 378489 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 5.3272. Min Range: -5.3272

Max Act: 4.7647. Min Act: -0.1700

Data Index: 859201 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 5.3272. Min Range: -5.3272

Max Act: 4.7959. Min Act: -0.1700

Data Index: 786300 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 5.3272. Min Range: -5.3272

Max Act: 4.7334. Min Act: -0.1700

Data Index: 760279 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 5.3272. Min Range: -5.3272

Max Act: 4.7022. Min Act: -0.1700

Data Index: 452413 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 5.3272. Min Range: -5.3272

Max Act: 4.7334. Min Act: -0.1700

Data Index: 1093417 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 5.3272. Min Range: -5.3272

Max Act: 4.7022. Min Act: -0.1700

Data Index: 768384 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 5.3272. Min Range: -5.3272

Max Act: 4.7022. Min Act: -0.1700

Data Index: 811811 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 5.3272. Min Range: -5.3272

Max Act: 4.6709. Min Act: -0.1700

Data Index: 29 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 5.3272. Min Range: -5.3272

Max Act: 4.6709. Min Act: -0.1700

Data Index: 664432 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 5.3272. Min Range: -5.3272

Max Act: 4.7022. Min Act: -0.1700

Data Index: 1165238 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 5.3272. Min Range: -5.3272

Max Act: 4.6084. Min Act: -0.1700

Data Index: 1022197 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 5.3272. Min Range: -5.3272

Max Act: 4.6709. Min Act: -0.1700

Data Index: 815457 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 5.3272. Min Range: -5.3272

Max Act: 4.6709. Min Act: -0.1700

Data Index: 626092 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 5.3272. Min Range: -5.3272

Max Act: 4.7022. Min Act: -0.1700

Data Index: 569923 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 5.3272. Min Range: -5.3272

Max Act: 4.6397. Min Act: -0.1700

Data Index: 843699 (C4 (Web Text))

Max Activating Token Index: 212