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

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

Neuron 207 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: 4.2164. Min Range: -4.2164

Max Act: 4.2164. Min Act: -0.1699

Data Index: 176958 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 4.2164. Min Range: -4.2164

Max Act: 4.1820. Min Act: -0.1700

Data Index: 824759 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 4.2164. Min Range: -4.2164

Max Act: 4.1705. Min Act: -0.1700

Data Index: 725688 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 4.2164. Min Range: -4.2164

Max Act: 4.1774. Min Act: -0.1700

Data Index: 638634 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 4.2164. Min Range: -4.2164

Max Act: 4.0471. Min Act: -0.1700

Data Index: 56616 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 4.2164. Min Range: -4.2164

Max Act: 4.0338. Min Act: -0.1700

Data Index: 1211569 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 4.2164. Min Range: -4.2164

Max Act: 4.0202. Min Act: -0.1700

Data Index: 1006250 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 4.2164. Min Range: -4.2164

Max Act: 4.0134. Min Act: -0.1700

Data Index: 84010 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 4.2164. Min Range: -4.2164

Max Act: 3.9824. Min Act: -0.1696

Data Index: 546505 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 4.2164. Min Range: -4.2164

Max Act: 3.9785. Min Act: -0.1700

Data Index: 271933 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 4.2164. Min Range: -4.2164

Max Act: 3.9853. Min Act: -0.1700

Data Index: 651865 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 4.2164. Min Range: -4.2164

Max Act: 3.9556. Min Act: -0.1700

Data Index: 193270 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 4.2164. Min Range: -4.2164

Max Act: 3.9382. Min Act: -0.1652

Data Index: 867289 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 4.2164. Min Range: -4.2164

Max Act: 3.9196. Min Act: -0.1700

Data Index: 417654 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 4.2164. Min Range: -4.2164

Max Act: 3.9258. Min Act: -0.1700

Data Index: 373083 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 4.2164. Min Range: -4.2164

Max Act: 3.9140. Min Act: -0.1609

Data Index: 32227 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 4.2164. Min Range: -4.2164

Max Act: 3.8886. Min Act: -0.1700

Data Index: 702000 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 4.2164. Min Range: -4.2164

Max Act: 3.9037. Min Act: -0.1700

Data Index: 929477 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 4.2164. Min Range: -4.2164

Max Act: 3.8896. Min Act: -0.1700

Data Index: 28697 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 4.2164. Min Range: -4.2164

Max Act: 3.8608. Min Act: -0.1700

Data Index: 503455 (C4 (Web Text))

Max Activating Token Index: 98