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

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

Neuron 21 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: 3.6646. Min Range: -3.6646

Max Act: 3.6646. Min Act: -0.1700

Data Index: 1233227 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 3.6646. Min Range: -3.6646

Max Act: 3.6646. Min Act: -0.1700

Data Index: 1306249 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 3.6646. Min Range: -3.6646

Max Act: 3.6333. Min Act: -0.1700

Data Index: 447238 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 3.6646. Min Range: -3.6646

Max Act: 3.6646. Min Act: -0.1700

Data Index: 823339 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 3.6646. Min Range: -3.6646

Max Act: 3.6333. Min Act: -0.1700

Data Index: 1087776 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 3.6646. Min Range: -3.6646

Max Act: 3.6020. Min Act: -0.1700

Data Index: 762432 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 3.6646. Min Range: -3.6646

Max Act: 3.6333. Min Act: -0.1700

Data Index: 473961 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 3.6646. Min Range: -3.6646

Max Act: 3.6333. Min Act: -0.1700

Data Index: 637319 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 3.6646. Min Range: -3.6646

Max Act: 3.6020. Min Act: -0.1700

Data Index: 459479 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 3.6646. Min Range: -3.6646

Max Act: 3.6020. Min Act: -0.1700

Data Index: 108307 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 3.6646. Min Range: -3.6646

Max Act: 3.6020. Min Act: -0.1700

Data Index: 1265508 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 3.6646. Min Range: -3.6646

Max Act: 3.5706. Min Act: -0.1700

Data Index: 791578 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 3.6646. Min Range: -3.6646

Max Act: 3.5706. Min Act: -0.1700

Data Index: 229626 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 3.6646. Min Range: -3.6646

Max Act: 3.6020. Min Act: -0.1700

Data Index: 264092 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 3.6646. Min Range: -3.6646

Max Act: 3.5706. Min Act: -0.1700

Data Index: 761943 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 3.6646. Min Range: -3.6646

Max Act: 3.5706. Min Act: -0.1700

Data Index: 518763 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 3.6646. Min Range: -3.6646

Max Act: 3.5706. Min Act: -0.1700

Data Index: 497515 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 3.6646. Min Range: -3.6646

Max Act: 3.5393. Min Act: -0.1700

Data Index: 1302399 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 3.6646. Min Range: -3.6646

Max Act: 3.5706. Min Act: -0.1700

Data Index: 661103 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 3.6646. Min Range: -3.6646

Max Act: 3.5393. Min Act: -0.1700

Data Index: 279260 (C4 (Web Text))

Max Activating Token Index: 812