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

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

Neuron 1619 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: 6.3022. Min Range: -6.3022

Max Act: 6.3022. Min Act: -0.1699

Data Index: 745354 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 6.3022. Min Range: -6.3022

Max Act: 5.9116. Min Act: -0.1699

Data Index: 968215 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 6.3022. Min Range: -6.3022

Max Act: 5.8647. Min Act: -0.1699

Data Index: 583184 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 6.3022. Min Range: -6.3022

Max Act: 5.6694. Min Act: -0.1699

Data Index: 820436 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 6.3022. Min Range: -6.3022

Max Act: 5.6928. Min Act: -0.1699

Data Index: 1568395 (Python Code)

Max Activating Token Index: 978

Text #5

Max Range: 6.3022. Min Range: -6.3022

Max Act: 5.6303. Min Act: -0.1699

Data Index: 724482 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 6.3022. Min Range: -6.3022

Max Act: 5.6225. Min Act: -0.1699

Data Index: 910587 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 6.3022. Min Range: -6.3022

Max Act: 5.6420. Min Act: -0.1699

Data Index: 124461 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 6.3022. Min Range: -6.3022

Max Act: 5.6420. Min Act: -0.1699

Data Index: 1283181 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 6.3022. Min Range: -6.3022

Max Act: 5.6030. Min Act: -0.1699

Data Index: 517618 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 6.3022. Min Range: -6.3022

Max Act: 5.6342. Min Act: -0.1699

Data Index: 1005236 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 6.3022. Min Range: -6.3022

Max Act: 5.5639. Min Act: -0.1699

Data Index: 429520 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 6.3022. Min Range: -6.3022

Max Act: 5.5795. Min Act: -0.1699

Data Index: 529410 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 6.3022. Min Range: -6.3022

Max Act: 5.4819. Min Act: -0.1699

Data Index: 182389 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 6.3022. Min Range: -6.3022

Max Act: 5.3803. Min Act: -0.1699

Data Index: 1347827 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 6.3022. Min Range: -6.3022

Max Act: 5.4350. Min Act: -0.1699

Data Index: 422198 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 6.3022. Min Range: -6.3022

Max Act: 5.4077. Min Act: -0.1699

Data Index: 430440 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 6.3022. Min Range: -6.3022

Max Act: 5.3803. Min Act: -0.1699

Data Index: 239724 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 6.3022. Min Range: -6.3022

Max Act: 5.3432. Min Act: -0.1699

Data Index: 1512166 (Python Code)

Max Activating Token Index: 793

Text #19

Max Range: 6.3022. Min Range: -6.3022

Max Act: 5.3842. Min Act: -0.1699

Data Index: 591354 (C4 (Web Text))

Max Activating Token Index: 258