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

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

Neuron 1631 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.3631. Min Act: -0.1700

Data Index: 814864 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.3318. Min Act: -0.1700

Data Index: 949001 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.3006. Min Act: -0.1700

Data Index: 865601 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.2693. Min Act: -0.1700

Data Index: 473122 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.2068. Min Act: -0.1700

Data Index: 48551 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.1756. Min Act: -0.1700

Data Index: 122812 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.2068. Min Act: -0.1700

Data Index: 216044 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.1443. Min Act: -0.1700

Data Index: 611107 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.1131. Min Act: -0.1700

Data Index: 124339 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.0818. Min Act: -0.1700

Data Index: 577738 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.1131. Min Act: -0.1700

Data Index: 102349 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.1131. Min Act: -0.1700

Data Index: 481128 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.0818. Min Act: -0.1700

Data Index: 325640 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.0506. Min Act: -0.1700

Data Index: 247759 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.0818. Min Act: -0.1700

Data Index: 307591 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.0506. Min Act: -0.1700

Data Index: 518962 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.1131. Min Act: -0.1700

Data Index: 704718 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.0506. Min Act: -0.1700

Data Index: 127760 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.0193. Min Act: -0.1700

Data Index: 755341 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 5.3631. Min Range: -5.3631

Max Act: 5.0506. Min Act: -0.1700

Data Index: 736787 (C4 (Web Text))

Max Activating Token Index: 272