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

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

Neuron 1793 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: 3.6338. Min Range: -3.6338

Max Act: 3.6338. Min Act: -0.1700

Data Index: 801361 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 3.6338. Min Range: -3.6338

Max Act: 3.4928. Min Act: -0.1700

Data Index: 244564 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 3.6338. Min Range: -3.6338

Max Act: 3.4413. Min Act: -0.1700

Data Index: 1340778 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 3.6338. Min Range: -3.6338

Max Act: 3.4700. Min Act: -0.1700

Data Index: 951260 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 3.6338. Min Range: -3.6338

Max Act: 3.4602. Min Act: -0.1700

Data Index: 192929 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 3.6338. Min Range: -3.6338

Max Act: 3.4493. Min Act: -0.1700

Data Index: 491638 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 3.6338. Min Range: -3.6338

Max Act: 3.4395. Min Act: -0.1700

Data Index: 289447 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 3.6338. Min Range: -3.6338

Max Act: 3.4340. Min Act: -0.1700

Data Index: 1254917 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 3.6338. Min Range: -3.6338

Max Act: 3.4237. Min Act: -0.1700

Data Index: 1231139 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 3.6338. Min Range: -3.6338

Max Act: 3.3889. Min Act: -0.1700

Data Index: 933622 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 3.6338. Min Range: -3.6338

Max Act: 3.4195. Min Act: -0.1700

Data Index: 4092 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 3.6338. Min Range: -3.6338

Max Act: 3.4333. Min Act: -0.1700

Data Index: 665558 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 3.6338. Min Range: -3.6338

Max Act: 3.4034. Min Act: -0.1700

Data Index: 1347249 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 3.6338. Min Range: -3.6338

Max Act: 3.4119. Min Act: -0.1700

Data Index: 590849 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 3.6338. Min Range: -3.6338

Max Act: 3.4191. Min Act: -0.1700

Data Index: 150895 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 3.6338. Min Range: -3.6338

Max Act: 3.4004. Min Act: -0.1700

Data Index: 1020609 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 3.6338. Min Range: -3.6338

Max Act: 3.3839. Min Act: -0.1700

Data Index: 1065902 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 3.6338. Min Range: -3.6338

Max Act: 3.4124. Min Act: -0.1700

Data Index: 502454 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 3.6338. Min Range: -3.6338

Max Act: 3.3801. Min Act: -0.1700

Data Index: 1309521 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 3.6338. Min Range: -3.6338

Max Act: 3.4042. Min Act: -0.1700

Data Index: 773726 (C4 (Web Text))

Max Activating Token Index: 710