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

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

Neuron 214 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: 5.6491. Min Range: -5.6491

Max Act: 5.6491. Min Act: -0.1700

Data Index: 1059936 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.5241. Min Act: -0.1700

Data Index: 767732 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.4928. Min Act: -0.1700

Data Index: 37642 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.4616. Min Act: -0.1700

Data Index: 1293393 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.3991. Min Act: -0.1700

Data Index: 99878 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.3991. Min Act: -0.1700

Data Index: 678927 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.3053. Min Act: -0.1700

Data Index: 848352 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.3678. Min Act: -0.1700

Data Index: 217547 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.3678. Min Act: -0.1700

Data Index: 827019 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.3053. Min Act: -0.1700

Data Index: 1051587 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.3053. Min Act: -0.1700

Data Index: 1301777 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.2741. Min Act: -0.1700

Data Index: 1269331 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.2116. Min Act: -0.1700

Data Index: 708148 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.1803. Min Act: -0.1700

Data Index: 991299 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.1803. Min Act: -0.1700

Data Index: 1200547 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.1803. Min Act: -0.1700

Data Index: 287373 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.2116. Min Act: -0.1700

Data Index: 374301 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.2116. Min Act: -0.1700

Data Index: 1051681 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.1803. Min Act: -0.1700

Data Index: 601901 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.1803. Min Act: -0.1700

Data Index: 127365 (C4 (Web Text))

Max Activating Token Index: 423