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

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

Neuron 938 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: 5.5003. Min Range: -5.5003

Max Act: 5.4690. Min Act: -0.1700

Data Index: 995894 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 5.5003. Min Range: -5.5003

Max Act: 5.5003. Min Act: -0.1700

Data Index: 1369044 (Python Code)

Max Activating Token Index: 238

Text #2

Max Range: 5.5003. Min Range: -5.5003

Max Act: 5.4378. Min Act: -0.1700

Data Index: 1163816 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 5.5003. Min Range: -5.5003

Max Act: 5.3440. Min Act: -0.1700

Data Index: 1623780 (Python Code)

Max Activating Token Index: 297

Text #4

Max Range: 5.5003. Min Range: -5.5003

Max Act: 5.4065. Min Act: -0.1700

Data Index: 532309 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 5.5003. Min Range: -5.5003

Max Act: 5.3440. Min Act: -0.1700

Data Index: 38992 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 5.5003. Min Range: -5.5003

Max Act: 5.2815. Min Act: -0.1700

Data Index: 368718 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 5.5003. Min Range: -5.5003

Max Act: 5.3128. Min Act: -0.1700

Data Index: 53533 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 5.5003. Min Range: -5.5003

Max Act: 5.2503. Min Act: -0.1700

Data Index: 1635318 (Python Code)

Max Activating Token Index: 304

Text #9

Max Range: 5.5003. Min Range: -5.5003

Max Act: 5.2503. Min Act: -0.1700

Data Index: 236300 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 5.5003. Min Range: -5.5003

Max Act: 5.1565. Min Act: -0.1700

Data Index: 1485721 (Python Code)

Max Activating Token Index: 673

Text #11

Max Range: 5.5003. Min Range: -5.5003

Max Act: 5.1565. Min Act: -0.1700

Data Index: 65548 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 5.5003. Min Range: -5.5003

Max Act: 5.1565. Min Act: -0.1700

Data Index: 1575426 (Python Code)

Max Activating Token Index: 809

Text #13

Max Range: 5.5003. Min Range: -5.5003

Max Act: 5.2503. Min Act: -0.1700

Data Index: 986568 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 5.5003. Min Range: -5.5003

Max Act: 5.1878. Min Act: -0.1700

Data Index: 963577 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 5.5003. Min Range: -5.5003

Max Act: 5.2190. Min Act: -0.1700

Data Index: 498752 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 5.5003. Min Range: -5.5003

Max Act: 5.2503. Min Act: -0.1700

Data Index: 273580 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 5.5003. Min Range: -5.5003

Max Act: 5.1878. Min Act: -0.1700

Data Index: 1514938 (Python Code)

Max Activating Token Index: 949

Text #18

Max Range: 5.5003. Min Range: -5.5003

Max Act: 5.1878. Min Act: -0.1700

Data Index: 1379484 (Python Code)

Max Activating Token Index: 18

Text #19

Max Range: 5.5003. Min Range: -5.5003

Max Act: 5.2190. Min Act: -0.1700

Data Index: 141691 (C4 (Web Text))

Max Activating Token Index: 469