Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 108 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.7512. Min Act: -0.1700

Data Index: 1285354 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.7199. Min Act: -0.1700

Data Index: 702002 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.5949. Min Act: -0.1700

Data Index: 758071 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.5637. Min Act: -0.1700

Data Index: 689734 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.5637. Min Act: -0.1700

Data Index: 449005 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.5324. Min Act: -0.1700

Data Index: 1093346 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.5324. Min Act: -0.1700

Data Index: 243276 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.5012. Min Act: -0.1700

Data Index: 1070776 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.5324. Min Act: -0.1700

Data Index: 834663 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.5324. Min Act: -0.1700

Data Index: 305177 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.5324. Min Act: -0.1700

Data Index: 949085 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.5012. Min Act: -0.1700

Data Index: 364972 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.5012. Min Act: -0.1700

Data Index: 801553 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.5012. Min Act: -0.1700

Data Index: 544259 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.5012. Min Act: -0.1699

Data Index: 1272456 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.5012. Min Act: -0.1700

Data Index: 555667 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.5012. Min Act: -0.1700

Data Index: 785791 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.4699. Min Act: -0.1700

Data Index: 563279 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.4699. Min Act: -0.1700

Data Index: 946769 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 5.7512. Min Range: -5.7512

Max Act: 5.4699. Min Act: -0.1700

Data Index: 1310390 (C4 (Web Text))

Max Activating Token Index: 242