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

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

Neuron 210 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: 5.0576. Min Range: -5.0576

Max Act: 5.0576. Min Act: -0.1700

Data Index: 936856 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 5.0576. Min Range: -5.0576

Max Act: 5.0264. Min Act: -0.1700

Data Index: 1071976 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.9951. Min Act: -0.1700

Data Index: 111188 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.9326. Min Act: -0.1700

Data Index: 165591 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.9326. Min Act: -0.1700

Data Index: 1159009 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.9639. Min Act: -0.1700

Data Index: 596901 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8701. Min Act: -0.1700

Data Index: 76856 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8076. Min Act: -0.1700

Data Index: 21463 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.7764. Min Act: -0.1700

Data Index: 279049 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8076. Min Act: -0.1693

Data Index: 956698 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8076. Min Act: -0.1700

Data Index: 223884 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.7764. Min Act: -0.1700

Data Index: 333395 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.7139. Min Act: -0.1700

Data Index: 584634 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.7139. Min Act: -0.1700

Data Index: 1321959 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.7451. Min Act: -0.1700

Data Index: 345109 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.7139. Min Act: -0.1700

Data Index: 692495 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.7139. Min Act: -0.1700

Data Index: 70264 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.7139. Min Act: -0.1700

Data Index: 633769 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.7139. Min Act: -0.1700

Data Index: 1064937 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.7139. Min Act: -0.1700

Data Index: 727929 (C4 (Web Text))

Max Activating Token Index: 950