Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 130 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 24.2055. Min Range: -24.2055

Max Act: 24.2055. Min Act: -0.1699

Data Index: 1075609 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 24.2055. Min Range: -24.2055

Max Act: 23.1951. Min Act: -0.1114

Data Index: 241657 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 24.2055. Min Range: -24.2055

Max Act: 22.6926. Min Act: -0.1063

Data Index: 157390 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 24.2055. Min Range: -24.2055

Max Act: 22.5997. Min Act: -0.1700

Data Index: 1372470 (Python Code)

Max Activating Token Index: 250

Text #4

Max Range: 24.2055. Min Range: -24.2055

Max Act: 22.3266. Min Act: -0.1259

Data Index: 694225 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 24.2055. Min Range: -24.2055

Max Act: 22.2849. Min Act: -0.1690

Data Index: 1232359 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 24.2055. Min Range: -24.2055

Max Act: 22.0930. Min Act: -0.1373

Data Index: 1317486 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 24.2055. Min Range: -24.2055

Max Act: 22.0991. Min Act: -0.1672

Data Index: 61990 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 24.2055. Min Range: -24.2055

Max Act: 21.9714. Min Act: -0.1699

Data Index: 1323574 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 24.2055. Min Range: -24.2055

Max Act: 22.0969. Min Act: -0.1673

Data Index: 1147649 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 24.2055. Min Range: -24.2055

Max Act: 21.9283. Min Act: -0.1690

Data Index: 165014 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 24.2055. Min Range: -24.2055

Max Act: 21.7747. Min Act: -0.1343

Data Index: 53404 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 24.2055. Min Range: -24.2055

Max Act: 21.7852. Min Act: -0.1699

Data Index: 397196 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 24.2055. Min Range: -24.2055

Max Act: 21.7406. Min Act: -0.1694

Data Index: 224075 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 24.2055. Min Range: -24.2055

Max Act: 21.6466. Min Act: -0.1699

Data Index: 145543 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 24.2055. Min Range: -24.2055

Max Act: 21.6583. Min Act: -0.1692

Data Index: 636574 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 24.2055. Min Range: -24.2055

Max Act: 21.6920. Min Act: -0.1695

Data Index: 251986 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 24.2055. Min Range: -24.2055

Max Act: 21.5775. Min Act: -0.1695

Data Index: 155363 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 24.2055. Min Range: -24.2055

Max Act: 21.5070. Min Act: 0.1839

Data Index: 739569 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 24.2055. Min Range: -24.2055

Max Act: 21.5373. Min Act: -0.1699

Data Index: 1236161 (C4 (Web Text))

Max Activating Token Index: 161