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

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

Neuron 508 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.3337. Min Act: -0.1700

Data Index: 442581 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.0978. Min Act: -0.1700

Data Index: 932810 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.0347. Min Act: -0.1700

Data Index: 194385 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.0031. Min Act: -0.1700

Data Index: 850049 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.9873. Min Act: -0.1700

Data Index: 475349 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.9239. Min Act: -0.1700

Data Index: 1098307 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.9714. Min Act: -0.1700

Data Index: 1127055 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.9398. Min Act: -0.1700

Data Index: 112525 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.9081. Min Act: -0.1700

Data Index: 427819 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.9081. Min Act: -0.1700

Data Index: 1111846 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.8922. Min Act: -0.1700

Data Index: 1102237 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.8763. Min Act: -0.1700

Data Index: 236408 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.8763. Min Act: -0.1700

Data Index: 588454 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.8763. Min Act: -0.1700

Data Index: 443629 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.8763. Min Act: -0.1700

Data Index: 1151048 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.8763. Min Act: -0.1700

Data Index: 169421 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.8605. Min Act: -0.1700

Data Index: 390311 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.8763. Min Act: -0.1700

Data Index: 848564 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.8446. Min Act: -0.1700

Data Index: 388540 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.8287. Min Act: -0.1700

Data Index: 750507 (C4 (Web Text))

Max Activating Token Index: 971