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

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

Neuron 1851 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: 3.6252. Min Range: -3.6252

Max Act: 3.6155. Min Act: -0.1700

Data Index: 89912 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.6252. Min Act: -0.1700

Data Index: 1052710 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.6165. Min Act: -0.1700

Data Index: 863081 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.5945. Min Act: -0.1700

Data Index: 842494 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.5972. Min Act: -0.1700

Data Index: 173723 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.5413. Min Act: -0.1700

Data Index: 1484674 (Python Code)

Max Activating Token Index: 176

Text #6

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.5599. Min Act: -0.1700

Data Index: 1048067 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.5408. Min Act: -0.1700

Data Index: 1000441 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.5504. Min Act: -0.1700

Data Index: 1211592 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.5316. Min Act: -0.1700

Data Index: 267634 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.5265. Min Act: -0.1700

Data Index: 1280359 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.5300. Min Act: -0.1700

Data Index: 33161 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.5370. Min Act: -0.1700

Data Index: 431611 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.5180. Min Act: -0.1700

Data Index: 770538 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.5286. Min Act: -0.1700

Data Index: 823652 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.5174. Min Act: -0.1700

Data Index: 758671 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.5196. Min Act: -0.1700

Data Index: 1327193 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.5184. Min Act: -0.1700

Data Index: 1189598 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.4942. Min Act: -0.1700

Data Index: 233508 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 3.6252. Min Range: -3.6252

Max Act: 3.4881. Min Act: -0.1700

Data Index: 707782 (C4 (Web Text))

Max Activating Token Index: 8