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

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

Neuron 976 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: 4.9361. Min Range: -4.9361

Max Act: 4.9361. Min Act: -0.1700

Data Index: 740850 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.9361. Min Range: -4.9361

Max Act: 4.9270. Min Act: -0.1700

Data Index: 376014 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.9361. Min Range: -4.9361

Max Act: 4.9060. Min Act: -0.1700

Data Index: 138145 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.9361. Min Range: -4.9361

Max Act: 4.8498. Min Act: -0.1700

Data Index: 594874 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.9361. Min Range: -4.9361

Max Act: 4.8363. Min Act: -0.1700

Data Index: 1208217 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 4.9361. Min Range: -4.9361

Max Act: 4.8158. Min Act: -0.1700

Data Index: 406386 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.9361. Min Range: -4.9361

Max Act: 4.8402. Min Act: -0.1700

Data Index: 717398 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 4.9361. Min Range: -4.9361

Max Act: 4.7900. Min Act: -0.1700

Data Index: 119451 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 4.9361. Min Range: -4.9361

Max Act: 4.8010. Min Act: -0.1700

Data Index: 1163462 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.9361. Min Range: -4.9361

Max Act: 4.7899. Min Act: -0.1700

Data Index: 661370 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.9361. Min Range: -4.9361

Max Act: 4.7951. Min Act: -0.1700

Data Index: 385677 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 4.9361. Min Range: -4.9361

Max Act: 4.8014. Min Act: -0.1700

Data Index: 1341386 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 4.9361. Min Range: -4.9361

Max Act: 4.7606. Min Act: -0.1700

Data Index: 396118 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 4.9361. Min Range: -4.9361

Max Act: 4.7657. Min Act: -0.1700

Data Index: 1163697 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 4.9361. Min Range: -4.9361

Max Act: 4.7693. Min Act: -0.1700

Data Index: 1245309 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 4.9361. Min Range: -4.9361

Max Act: 4.7794. Min Act: -0.1700

Data Index: 22957 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.9361. Min Range: -4.9361

Max Act: 4.7571. Min Act: -0.1700

Data Index: 538549 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 4.9361. Min Range: -4.9361

Max Act: 4.7225. Min Act: -0.1700

Data Index: 300980 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 4.9361. Min Range: -4.9361

Max Act: 4.7290. Min Act: -0.1700

Data Index: 74888 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 4.9361. Min Range: -4.9361

Max Act: 4.7331. Min Act: -0.1700

Data Index: 800435 (C4 (Web Text))

Max Activating Token Index: 1023