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

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

Neuron 1233 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: 3.5280. Min Range: -3.5280

Max Act: 3.5280. Min Act: -0.1700

Data Index: 474758 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.5280. Min Act: -0.1700

Data Index: 685840 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.5280. Min Act: -0.1700

Data Index: 252371 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3555. Min Act: -0.1700

Data Index: 820810 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3398. Min Act: -0.1700

Data Index: 923517 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3555. Min Act: -0.1700

Data Index: 290738 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3555. Min Act: -0.1700

Data Index: 1586637 (Python Code)

Max Activating Token Index: 750

Text #7

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.2770. Min Act: -0.1700

Data Index: 1352167 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.2770. Min Act: -0.1700

Data Index: 585675 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3712. Min Act: -0.1700

Data Index: 363678 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3398. Min Act: -0.1700

Data Index: 322155 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.2456. Min Act: -0.1700

Data Index: 839402 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.2770. Min Act: -0.1700

Data Index: 905503 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.2770. Min Act: -0.1700

Data Index: 838764 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.1984. Min Act: -0.1700

Data Index: 958280 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3712. Min Act: -0.1700

Data Index: 1018559 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.2927. Min Act: -0.1700

Data Index: 1223177 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.2613. Min Act: -0.1700

Data Index: 574896 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.2613. Min Act: -0.1700

Data Index: 966589 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.2299. Min Act: -0.1700

Data Index: 17784 (C4 (Web Text))

Max Activating Token Index: 954