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

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

Neuron 36 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.4384. Min Act: -0.1700

Data Index: 601684 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.3756. Min Act: -0.1700

Data Index: 1176063 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2657. Min Act: -0.1700

Data Index: 446833 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2500. Min Act: -0.1700

Data Index: 767051 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2186. Min Act: -0.1700

Data Index: 1066266 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2028. Min Act: -0.1700

Data Index: 607678 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.1871. Min Act: -0.1700

Data Index: 1072491 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.1871. Min Act: -0.1700

Data Index: 820479 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.1871. Min Act: -0.1700

Data Index: 563115 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.1871. Min Act: -0.1700

Data Index: 672183 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.1713. Min Act: -0.1700

Data Index: 320658 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.1556. Min Act: -0.1700

Data Index: 535585 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.1871. Min Act: -0.1700

Data Index: 931651 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.1556. Min Act: -0.1700

Data Index: 1086629 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.1241. Min Act: -0.1700

Data Index: 759807 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.1241. Min Act: -0.1700

Data Index: 746522 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.1241. Min Act: -0.1700

Data Index: 366042 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.1241. Min Act: -0.1700

Data Index: 17299 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.1241. Min Act: -0.1700

Data Index: 830724 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.1399. Min Act: -0.1700

Data Index: 644372 (C4 (Web Text))

Max Activating Token Index: 516