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

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

Neuron 1607 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.6678. Min Act: -0.1700

Data Index: 1185270 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.5582. Min Act: -0.1700

Data Index: 490404 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.6209. Min Act: -0.1700

Data Index: 510260 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.5426. Min Act: -0.1700

Data Index: 313683 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.5582. Min Act: -0.1700

Data Index: 833174 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.5895. Min Act: -0.1700

Data Index: 820429 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.5582. Min Act: -0.1700

Data Index: 126667 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.5739. Min Act: -0.1700

Data Index: 543139 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.5426. Min Act: -0.1700

Data Index: 173919 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.5426. Min Act: -0.1700

Data Index: 900737 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.5269. Min Act: -0.1700

Data Index: 571840 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.5112. Min Act: -0.1700

Data Index: 1356585 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.5112. Min Act: -0.1700

Data Index: 414177 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.5112. Min Act: -0.1700

Data Index: 37482 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.5269. Min Act: -0.1700

Data Index: 1337169 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.4956. Min Act: -0.1700

Data Index: 219699 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.4329. Min Act: -0.1700

Data Index: 1242942 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.4642. Min Act: -0.1700

Data Index: 815789 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.4485. Min Act: -0.1700

Data Index: 810234 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 3.6678. Min Range: -3.6678

Max Act: 3.4642. Min Act: -0.1700

Data Index: 792746 (C4 (Web Text))

Max Activating Token Index: 58