Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 593 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.9409. Min Act: -0.1700

Data Index: 155113 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.9097. Min Act: -0.1700

Data Index: 1332804 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.9097. Min Act: -0.1700

Data Index: 699906 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.8784. Min Act: -0.1700

Data Index: 761498 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.9097. Min Act: -0.1700

Data Index: 49433 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.7847. Min Act: -0.1700

Data Index: 1300464 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.7222. Min Act: -0.1700

Data Index: 324412 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.7847. Min Act: -0.1700

Data Index: 847131 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.7222. Min Act: -0.1700

Data Index: 931670 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.7847. Min Act: -0.1700

Data Index: 459459 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.7847. Min Act: -0.1700

Data Index: 857778 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.7222. Min Act: -0.1700

Data Index: 1305140 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.7222. Min Act: -0.1700

Data Index: 1185834 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.7534. Min Act: -0.1700

Data Index: 1207794 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.6909. Min Act: -0.1700

Data Index: 209164 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.7534. Min Act: -0.1700

Data Index: 635685 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.7222. Min Act: -0.1700

Data Index: 1293617 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.7534. Min Act: -0.1700

Data Index: 1072261 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.7222. Min Act: -0.1700

Data Index: 497953 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 5.9409. Min Range: -5.9409

Max Act: 5.7222. Min Act: -0.1700

Data Index: 755578 (C4 (Web Text))

Max Activating Token Index: 626