Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 130 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.8748. Min Act: -0.1700

Data Index: 1359922 (Python Code)

Max Activating Token Index: 237

Text #1

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.7811. Min Act: -0.1700

Data Index: 1484481 (Python Code)

Max Activating Token Index: 887

Text #2

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.6561. Min Act: -0.1700

Data Index: 1596260 (Python Code)

Max Activating Token Index: 637

Text #3

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.6873. Min Act: -0.1700

Data Index: 1602875 (Python Code)

Max Activating Token Index: 718

Text #4

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.6561. Min Act: -0.1700

Data Index: 1656790 (Python Code)

Max Activating Token Index: 771

Text #5

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.5311. Min Act: -0.1700

Data Index: 1418590 (Python Code)

Max Activating Token Index: 963

Text #6

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.4686. Min Act: -0.1700

Data Index: 1466142 (Python Code)

Max Activating Token Index: 109

Text #7

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.5311. Min Act: -0.1700

Data Index: 1609291 (Python Code)

Max Activating Token Index: 520

Text #8

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.5623. Min Act: -0.1700

Data Index: 1655554 (Python Code)

Max Activating Token Index: 581

Text #9

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.4686. Min Act: -0.1700

Data Index: 1399783 (Python Code)

Max Activating Token Index: 204

Text #10

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.4686. Min Act: -0.1700

Data Index: 1385610 (Python Code)

Max Activating Token Index: 872

Text #11

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.5311. Min Act: -0.1700

Data Index: 1632888 (Python Code)

Max Activating Token Index: 347

Text #12

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.4373. Min Act: -0.1700

Data Index: 1631327 (Python Code)

Max Activating Token Index: 640

Text #13

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.4686. Min Act: -0.1700

Data Index: 1554247 (Python Code)

Max Activating Token Index: 284

Text #14

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.4373. Min Act: -0.1700

Data Index: 1510349 (Python Code)

Max Activating Token Index: 889

Text #15

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.4373. Min Act: -0.1700

Data Index: 1507411 (Python Code)

Max Activating Token Index: 123

Text #16

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.4373. Min Act: -0.1700

Data Index: 1576615 (Python Code)

Max Activating Token Index: 830

Text #17

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.3748. Min Act: -0.1700

Data Index: 1639240 (Python Code)

Max Activating Token Index: 704

Text #18

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.4373. Min Act: -0.1700

Data Index: 1569808 (Python Code)

Max Activating Token Index: 336

Text #19

Max Range: 5.8748. Min Range: -5.8748

Max Act: 5.4373. Min Act: -0.1700

Data Index: 1466283 (Python Code)

Max Activating Token Index: 918