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

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

Neuron 1376 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.9406. Min Act: -0.1700

Data Index: 1267084 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.8155. Min Act: -0.1700

Data Index: 375681 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.7843. Min Act: -0.1700

Data Index: 1145162 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.6591. Min Act: -0.1700

Data Index: 816423 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.5965. Min Act: -0.1700

Data Index: 1318327 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.5338. Min Act: -0.1700

Data Index: 135889 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.5652. Min Act: -0.1700

Data Index: 1031514 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.4712. Min Act: -0.1700

Data Index: 866976 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.5338. Min Act: -0.1700

Data Index: 1281343 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.5025. Min Act: -0.1700

Data Index: 453824 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.4398. Min Act: -0.1700

Data Index: 743758 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.4398. Min Act: -0.1700

Data Index: 1195397 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.4398. Min Act: -0.1700

Data Index: 992919 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.4712. Min Act: -0.1700

Data Index: 26253 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.3143. Min Act: -0.1700

Data Index: 77334 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.3771. Min Act: -0.1700

Data Index: 601387 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.4398. Min Act: -0.1700

Data Index: 303114 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.3457. Min Act: -0.1700

Data Index: 732992 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.3771. Min Act: -0.1700

Data Index: 909750 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 3.9406. Min Range: -3.9406

Max Act: 3.3771. Min Act: -0.1700

Data Index: 736193 (C4 (Web Text))

Max Activating Token Index: 495