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

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

Neuron 36 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: 3.4222. Min Range: -3.4222

Max Act: 3.4222. Min Act: -0.1700

Data Index: 1000760 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 3.4222. Min Range: -3.4222

Max Act: 3.2513. Min Act: -0.1700

Data Index: 59915 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 3.4222. Min Range: -3.4222

Max Act: 3.2293. Min Act: -0.1700

Data Index: 84858 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 3.4222. Min Range: -3.4222

Max Act: 3.2195. Min Act: -0.1700

Data Index: 931705 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 3.4222. Min Range: -3.4222

Max Act: 3.2118. Min Act: -0.1700

Data Index: 223208 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 3.4222. Min Range: -3.4222

Max Act: 3.1967. Min Act: -0.1700

Data Index: 193440 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 3.4222. Min Range: -3.4222

Max Act: 3.1907. Min Act: -0.1700

Data Index: 1105855 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 3.4222. Min Range: -3.4222

Max Act: 3.1907. Min Act: -0.1700

Data Index: 103737 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 3.4222. Min Range: -3.4222

Max Act: 3.1789. Min Act: -0.1700

Data Index: 478143 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 3.4222. Min Range: -3.4222

Max Act: 3.1887. Min Act: -0.1700

Data Index: 510564 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 3.4222. Min Range: -3.4222

Max Act: 3.1793. Min Act: -0.1700

Data Index: 168982 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 3.4222. Min Range: -3.4222

Max Act: 3.1930. Min Act: -0.1700

Data Index: 437713 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 3.4222. Min Range: -3.4222

Max Act: 3.1717. Min Act: -0.1700

Data Index: 837155 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 3.4222. Min Range: -3.4222

Max Act: 3.1677. Min Act: -0.1700

Data Index: 517397 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 3.4222. Min Range: -3.4222

Max Act: 3.1508. Min Act: -0.1699

Data Index: 858326 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 3.4222. Min Range: -3.4222

Max Act: 3.1583. Min Act: -0.1700

Data Index: 250800 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 3.4222. Min Range: -3.4222

Max Act: 3.1553. Min Act: -0.1700

Data Index: 548909 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 3.4222. Min Range: -3.4222

Max Act: 3.1532. Min Act: -0.1700

Data Index: 761056 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 3.4222. Min Range: -3.4222

Max Act: 3.1377. Min Act: -0.1700

Data Index: 610522 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 3.4222. Min Range: -3.4222

Max Act: 3.1401. Min Act: -0.1700

Data Index: 1088956 (C4 (Web Text))

Max Activating Token Index: 78