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

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

Neuron 1608 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: 2.8800. Min Range: -2.8800

Max Act: 2.8800. Min Act: -0.1700

Data Index: 741719 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 2.8800. Min Range: -2.8800

Max Act: 2.7611. Min Act: -0.1700

Data Index: 719146 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 2.8800. Min Range: -2.8800

Max Act: 2.6649. Min Act: -0.1700

Data Index: 218686 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 2.8800. Min Range: -2.8800

Max Act: 2.6615. Min Act: -0.1700

Data Index: 653843 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 2.8800. Min Range: -2.8800

Max Act: 2.6437. Min Act: -0.1700

Data Index: 953975 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 2.8800. Min Range: -2.8800

Max Act: 2.6522. Min Act: -0.1700

Data Index: 689397 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 2.8800. Min Range: -2.8800

Max Act: 2.6388. Min Act: -0.1700

Data Index: 838099 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 2.8800. Min Range: -2.8800

Max Act: 2.6511. Min Act: -0.1700

Data Index: 917038 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 2.8800. Min Range: -2.8800

Max Act: 2.6376. Min Act: -0.1700

Data Index: 774440 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 2.8800. Min Range: -2.8800

Max Act: 2.6180. Min Act: -0.1700

Data Index: 804130 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 2.8800. Min Range: -2.8800

Max Act: 2.6340. Min Act: -0.1700

Data Index: 650902 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 2.8800. Min Range: -2.8800

Max Act: 2.6271. Min Act: -0.1700

Data Index: 1294371 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 2.8800. Min Range: -2.8800

Max Act: 2.6290. Min Act: -0.1700

Data Index: 323920 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 2.8800. Min Range: -2.8800

Max Act: 2.6157. Min Act: -0.1700

Data Index: 1586091 (Python Code)

Max Activating Token Index: 344

Text #14

Max Range: 2.8800. Min Range: -2.8800

Max Act: 2.6069. Min Act: -0.1700

Data Index: 216086 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 2.8800. Min Range: -2.8800

Max Act: 2.6002. Min Act: -0.1700

Data Index: 1228751 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 2.8800. Min Range: -2.8800

Max Act: 2.5943. Min Act: -0.1700

Data Index: 1334134 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 2.8800. Min Range: -2.8800

Max Act: 2.5994. Min Act: -0.1700

Data Index: 519728 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 2.8800. Min Range: -2.8800

Max Act: 2.5909. Min Act: -0.1700

Data Index: 1369485 (Python Code)

Max Activating Token Index: 1013

Text #19

Max Range: 2.8800. Min Range: -2.8800

Max Act: 2.6050. Min Act: -0.1700

Data Index: 1153114 (C4 (Web Text))

Max Activating Token Index: 581