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

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

Neuron 704 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: 3.4381. Min Range: -3.4381

Max Act: 3.4381. Min Act: -0.1700

Data Index: 1009945 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3910. Min Act: -0.1700

Data Index: 1474508 (Python Code)

Max Activating Token Index: 762

Text #2

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3597. Min Act: -0.1700

Data Index: 470186 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3754. Min Act: -0.1700

Data Index: 1499312 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3440. Min Act: -0.1700

Data Index: 1384156 (Python Code)

Max Activating Token Index: 675

Text #5

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3754. Min Act: -0.1700

Data Index: 1632217 (Python Code)

Max Activating Token Index: 598

Text #6

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3440. Min Act: -0.1700

Data Index: 1421609 (Python Code)

Max Activating Token Index: 142

Text #7

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3597. Min Act: -0.1700

Data Index: 1614990 (Python Code)

Max Activating Token Index: 696

Text #8

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3440. Min Act: -0.1700

Data Index: 13071 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3440. Min Act: -0.1700

Data Index: 708935 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2969. Min Act: -0.1700

Data Index: 37003 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3754. Min Act: -0.1700

Data Index: 1392765 (Python Code)

Max Activating Token Index: 690

Text #12

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3597. Min Act: -0.1700

Data Index: 1450293 (Python Code)

Max Activating Token Index: 636

Text #13

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3283. Min Act: -0.1700

Data Index: 1375611 (Python Code)

Max Activating Token Index: 716

Text #14

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3754. Min Act: -0.1700

Data Index: 1480277 (Python Code)

Max Activating Token Index: 252

Text #15

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3283. Min Act: -0.1700

Data Index: 1487979 (Python Code)

Max Activating Token Index: 421

Text #16

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3283. Min Act: -0.1700

Data Index: 1495485 (Python Code)

Max Activating Token Index: 125

Text #17

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3283. Min Act: -0.1700

Data Index: 294498 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3440. Min Act: -0.1700

Data Index: 1607785 (Python Code)

Max Activating Token Index: 356

Text #19

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3440. Min Act: -0.1700

Data Index: 1567941 (Python Code)

Max Activating Token Index: 772