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

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

Neuron 1606 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: 5.6935. Min Range: -5.6935

Max Act: 5.6935. Min Act: -0.1700

Data Index: 921842 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 5.6935. Min Range: -5.6935

Max Act: 5.6310. Min Act: -0.1700

Data Index: 309513 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 5.6935. Min Range: -5.6935

Max Act: 5.6623. Min Act: -0.1697

Data Index: 424988 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 5.6935. Min Range: -5.6935

Max Act: 5.5685. Min Act: -0.1700

Data Index: 220013 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 5.6935. Min Range: -5.6935

Max Act: 5.5998. Min Act: -0.1700

Data Index: 2943 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 5.6935. Min Range: -5.6935

Max Act: 5.5060. Min Act: -0.1700

Data Index: 589673 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 5.6935. Min Range: -5.6935

Max Act: 5.5373. Min Act: -0.1699

Data Index: 413058 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 5.6935. Min Range: -5.6935

Max Act: 5.4748. Min Act: -0.1699

Data Index: 862848 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 5.6935. Min Range: -5.6935

Max Act: 5.5373. Min Act: -0.1700

Data Index: 617825 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 5.6935. Min Range: -5.6935

Max Act: 5.4748. Min Act: -0.1700

Data Index: 869567 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 5.6935. Min Range: -5.6935

Max Act: 5.4435. Min Act: -0.1700

Data Index: 1296348 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 5.6935. Min Range: -5.6935

Max Act: 5.4123. Min Act: -0.1700

Data Index: 1122214 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 5.6935. Min Range: -5.6935

Max Act: 5.3810. Min Act: -0.1699

Data Index: 335869 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 5.6935. Min Range: -5.6935

Max Act: 5.3810. Min Act: -0.1700

Data Index: 913569 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 5.6935. Min Range: -5.6935

Max Act: 5.3498. Min Act: -0.1700

Data Index: 630003 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 5.6935. Min Range: -5.6935

Max Act: 5.3810. Min Act: -0.1699

Data Index: 1091945 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 5.6935. Min Range: -5.6935

Max Act: 5.2560. Min Act: -0.1699

Data Index: 1091268 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 5.6935. Min Range: -5.6935

Max Act: 5.2873. Min Act: -0.1699

Data Index: 817963 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 5.6935. Min Range: -5.6935

Max Act: 5.2873. Min Act: -0.1700

Data Index: 361889 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 5.6935. Min Range: -5.6935

Max Act: 5.4435. Min Act: -0.1700

Data Index: 627235 (C4 (Web Text))

Max Activating Token Index: 300