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

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

Neuron 900 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: 3.5693. Min Range: -3.5693

Max Act: 3.5693. Min Act: -0.1700

Data Index: 844704 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.5247. Min Act: -0.1700

Data Index: 127412 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4815. Min Act: -0.1700

Data Index: 337022 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4606. Min Act: -0.1700

Data Index: 194807 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4455. Min Act: -0.1700

Data Index: 1000085 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4414. Min Act: -0.1700

Data Index: 423524 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4214. Min Act: -0.1700

Data Index: 972503 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4021. Min Act: -0.1700

Data Index: 1263493 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4010. Min Act: -0.1700

Data Index: 82749 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3784. Min Act: -0.1700

Data Index: 44916 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3901. Min Act: -0.1700

Data Index: 328305 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3669. Min Act: -0.1700

Data Index: 973664 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3619. Min Act: -0.1700

Data Index: 893896 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3650. Min Act: -0.1700

Data Index: 704322 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3469. Min Act: -0.1700

Data Index: 724354 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3368. Min Act: -0.1700

Data Index: 147037 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3364. Min Act: -0.1700

Data Index: 1219442 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3328. Min Act: -0.1700

Data Index: 301133 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3470. Min Act: -0.1700

Data Index: 955798 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3405. Min Act: -0.1700

Data Index: 1024937 (C4 (Web Text))

Max Activating Token Index: 971