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

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

Neuron 1899 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: 3.4531. Min Range: -3.4531

Max Act: 3.4531. Min Act: -0.1700

Data Index: 465357 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 3.4531. Min Range: -3.4531

Max Act: 3.4375. Min Act: -0.1700

Data Index: 1266604 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 3.4531. Min Range: -3.4531

Max Act: 3.4218. Min Act: -0.1700

Data Index: 101593 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 3.4531. Min Range: -3.4531

Max Act: 3.4218. Min Act: -0.1700

Data Index: 582034 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 3.4531. Min Range: -3.4531

Max Act: 3.3904. Min Act: -0.1700

Data Index: 1084787 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 3.4531. Min Range: -3.4531

Max Act: 3.3904. Min Act: -0.1700

Data Index: 133915 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 3.4531. Min Range: -3.4531

Max Act: 3.3904. Min Act: -0.1700

Data Index: 867650 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 3.4531. Min Range: -3.4531

Max Act: 3.3590. Min Act: -0.1700

Data Index: 1045832 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 3.4531. Min Range: -3.4531

Max Act: 3.3277. Min Act: -0.1700

Data Index: 836430 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 3.4531. Min Range: -3.4531

Max Act: 3.3590. Min Act: -0.1700

Data Index: 1125954 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 3.4531. Min Range: -3.4531

Max Act: 3.3277. Min Act: -0.1700

Data Index: 582174 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 3.4531. Min Range: -3.4531

Max Act: 3.3120. Min Act: -0.1700

Data Index: 768354 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 3.4531. Min Range: -3.4531

Max Act: 3.2962. Min Act: -0.1700

Data Index: 166463 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 3.4531. Min Range: -3.4531

Max Act: 3.2805. Min Act: -0.1700

Data Index: 991510 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 3.4531. Min Range: -3.4531

Max Act: 3.2648. Min Act: -0.1700

Data Index: 1300334 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 3.4531. Min Range: -3.4531

Max Act: 3.2491. Min Act: -0.1700

Data Index: 201460 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 3.4531. Min Range: -3.4531

Max Act: 3.2334. Min Act: -0.1700

Data Index: 1580764 (Python Code)

Max Activating Token Index: 551

Text #17

Max Range: 3.4531. Min Range: -3.4531

Max Act: 3.2177. Min Act: -0.1700

Data Index: 188717 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 3.4531. Min Range: -3.4531

Max Act: 3.2177. Min Act: -0.1700

Data Index: 828825 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 3.4531. Min Range: -3.4531

Max Act: 3.2177. Min Act: -0.1700

Data Index: 538379 (C4 (Web Text))

Max Activating Token Index: 294