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

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

Neuron 709 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: 5.6934. Min Range: -5.6934

Max Act: 5.6934. Min Act: -0.1700

Data Index: 18881 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 5.6934. Min Range: -5.6934

Max Act: 5.6309. Min Act: -0.1700

Data Index: 1273497 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 5.6934. Min Range: -5.6934

Max Act: 5.5997. Min Act: -0.1700

Data Index: 1251469 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 5.6934. Min Range: -5.6934

Max Act: 5.5997. Min Act: -0.1700

Data Index: 1284873 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 5.6934. Min Range: -5.6934

Max Act: 5.5372. Min Act: -0.1700

Data Index: 1345322 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 5.6934. Min Range: -5.6934

Max Act: 5.5059. Min Act: -0.1700

Data Index: 739280 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 5.6934. Min Range: -5.6934

Max Act: 5.5372. Min Act: -0.1700

Data Index: 1190944 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 5.6934. Min Range: -5.6934

Max Act: 5.4434. Min Act: -0.1700

Data Index: 504058 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 5.6934. Min Range: -5.6934

Max Act: 5.4434. Min Act: -0.1699

Data Index: 255630 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 5.6934. Min Range: -5.6934

Max Act: 5.4747. Min Act: -0.1700

Data Index: 523292 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 5.6934. Min Range: -5.6934

Max Act: 5.4434. Min Act: -0.1700

Data Index: 100849 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 5.6934. Min Range: -5.6934

Max Act: 5.3809. Min Act: -0.1700

Data Index: 742963 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 5.6934. Min Range: -5.6934

Max Act: 5.3809. Min Act: -0.1700

Data Index: 22911 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 5.6934. Min Range: -5.6934

Max Act: 5.3184. Min Act: -0.1700

Data Index: 582393 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 5.6934. Min Range: -5.6934

Max Act: 5.3809. Min Act: -0.1700

Data Index: 423834 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 5.6934. Min Range: -5.6934

Max Act: 5.3497. Min Act: -0.1700

Data Index: 472078 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 5.6934. Min Range: -5.6934

Max Act: 5.3497. Min Act: -0.1700

Data Index: 78293 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 5.6934. Min Range: -5.6934

Max Act: 5.3184. Min Act: -0.1700

Data Index: 1332054 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 5.6934. Min Range: -5.6934

Max Act: 5.3184. Min Act: -0.1700

Data Index: 17858 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 5.6934. Min Range: -5.6934

Max Act: 5.3184. Min Act: -0.1700

Data Index: 336831 (C4 (Web Text))

Max Activating Token Index: 80