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

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

Neuron 349 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: 5.9822. Min Range: -5.9822

Max Act: 5.9822. Min Act: -0.1700

Data Index: 1297465 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 5.9822. Min Range: -5.9822

Max Act: 5.9510. Min Act: -0.1700

Data Index: 531824 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 5.9822. Min Range: -5.9822

Max Act: 5.9510. Min Act: -0.1700

Data Index: 959601 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 5.9822. Min Range: -5.9822

Max Act: 5.8572. Min Act: -0.1700

Data Index: 238013 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 5.9822. Min Range: -5.9822

Max Act: 5.8572. Min Act: -0.1700

Data Index: 746118 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 5.9822. Min Range: -5.9822

Max Act: 5.8260. Min Act: -0.1700

Data Index: 96180 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 5.9822. Min Range: -5.9822

Max Act: 5.8572. Min Act: -0.1700

Data Index: 604092 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 5.9822. Min Range: -5.9822

Max Act: 5.7947. Min Act: -0.1700

Data Index: 759071 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 5.9822. Min Range: -5.9822

Max Act: 5.7947. Min Act: -0.1700

Data Index: 1330217 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 5.9822. Min Range: -5.9822

Max Act: 5.7947. Min Act: -0.1700

Data Index: 1151098 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 5.9822. Min Range: -5.9822

Max Act: 5.7635. Min Act: -0.1700

Data Index: 455163 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 5.9822. Min Range: -5.9822

Max Act: 5.7010. Min Act: -0.1700

Data Index: 285483 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 5.9822. Min Range: -5.9822

Max Act: 5.7322. Min Act: -0.1700

Data Index: 478591 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 5.9822. Min Range: -5.9822

Max Act: 5.7322. Min Act: -0.1700

Data Index: 59097 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 5.9822. Min Range: -5.9822

Max Act: 5.7322. Min Act: -0.1700

Data Index: 1274727 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 5.9822. Min Range: -5.9822

Max Act: 5.7635. Min Act: -0.1700

Data Index: 1179669 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 5.9822. Min Range: -5.9822

Max Act: 5.7322. Min Act: -0.1700

Data Index: 590327 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 5.9822. Min Range: -5.9822

Max Act: 5.7010. Min Act: -0.1700

Data Index: 333949 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 5.9822. Min Range: -5.9822

Max Act: 5.6697. Min Act: -0.1700

Data Index: 1178984 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 5.9822. Min Range: -5.9822

Max Act: 5.6385. Min Act: -0.1700

Data Index: 1168141 (C4 (Web Text))

Max Activating Token Index: 668