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

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

Neuron 1312 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: 3.9883. Min Range: -3.9883

Max Act: 3.9883. Min Act: -0.1472

Data Index: 845888 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.9592. Min Act: -0.1700

Data Index: 118880 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8789. Min Act: -0.1700

Data Index: 510258 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8833. Min Act: -0.1699

Data Index: 168217 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8310. Min Act: -0.1700

Data Index: 731389 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8451. Min Act: -0.1700

Data Index: 895988 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8438. Min Act: -0.1700

Data Index: 551658 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8509. Min Act: -0.1700

Data Index: 613615 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8112. Min Act: -0.0866

Data Index: 66408 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7854. Min Act: -0.1651

Data Index: 28646 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8072. Min Act: -0.1698

Data Index: 1012870 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8116. Min Act: -0.1700

Data Index: 1173103 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7866. Min Act: -0.1700

Data Index: 153092 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7834. Min Act: -0.1664

Data Index: 589512 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7594. Min Act: -0.1700

Data Index: 839566 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7642. Min Act: -0.1700

Data Index: 308557 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7559. Min Act: -0.1700

Data Index: 783679 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7801. Min Act: -0.1700

Data Index: 600366 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7473. Min Act: -0.1700

Data Index: 302732 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7306. Min Act: -0.1663

Data Index: 131371 (C4 (Web Text))

Max Activating Token Index: 276