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

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

Neuron 1962 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.8370. Min Act: -0.1700

Data Index: 1011488 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.8213. Min Act: -0.1700

Data Index: 400256 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.7901. Min Act: -0.1700

Data Index: 185140 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6805. Min Act: -0.1700

Data Index: 347040 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.7431. Min Act: -0.1700

Data Index: 553056 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6649. Min Act: -0.1700

Data Index: 270623 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.7431. Min Act: -0.1700

Data Index: 1138834 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6336. Min Act: -0.1700

Data Index: 758076 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6023. Min Act: -0.1700

Data Index: 356702 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6962. Min Act: -0.1700

Data Index: 1027140 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6962. Min Act: -0.1700

Data Index: 1094766 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6649. Min Act: -0.1700

Data Index: 759485 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6179. Min Act: -0.1700

Data Index: 1116706 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6492. Min Act: -0.1700

Data Index: 52001 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6179. Min Act: -0.1700

Data Index: 1336145 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6649. Min Act: -0.1700

Data Index: 912249 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6336. Min Act: -0.1700

Data Index: 259534 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6179. Min Act: -0.1700

Data Index: 592445 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6649. Min Act: -0.1700

Data Index: 497955 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 3.8370. Min Range: -3.8370

Max Act: 3.6336. Min Act: -0.1700

Data Index: 508027 (C4 (Web Text))

Max Activating Token Index: 896