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

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

Neuron 720 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.1755. Min Range: -3.1755

Max Act: 3.1755. Min Act: -0.1700

Data Index: 588196 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 3.1755. Min Range: -3.1755

Max Act: 3.1755. Min Act: -0.1700

Data Index: 796412 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 3.1755. Min Range: -3.1755

Max Act: 3.1441. Min Act: -0.1700

Data Index: 314482 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 3.1755. Min Range: -3.1755

Max Act: 3.1441. Min Act: -0.1700

Data Index: 307119 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 3.1755. Min Range: -3.1755

Max Act: 3.0810. Min Act: -0.1700

Data Index: 34310 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 3.1755. Min Range: -3.1755

Max Act: 3.0810. Min Act: -0.1700

Data Index: 1141600 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 3.1755. Min Range: -3.1755

Max Act: 3.0494. Min Act: -0.1700

Data Index: 1457524 (Python Code)

Max Activating Token Index: 299

Text #7

Max Range: 3.1755. Min Range: -3.1755

Max Act: 3.0337. Min Act: -0.1700

Data Index: 1043170 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 3.1755. Min Range: -3.1755

Max Act: 3.0179. Min Act: -0.1700

Data Index: 992540 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 3.1755. Min Range: -3.1755

Max Act: 3.0179. Min Act: -0.1700

Data Index: 657034 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 3.1755. Min Range: -3.1755

Max Act: 3.0179. Min Act: -0.1700

Data Index: 1086598 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 3.1755. Min Range: -3.1755

Max Act: 3.0021. Min Act: -0.1700

Data Index: 48656 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 3.1755. Min Range: -3.1755

Max Act: 3.0179. Min Act: -0.1700

Data Index: 396675 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 3.1755. Min Range: -3.1755

Max Act: 3.0021. Min Act: -0.1700

Data Index: 694628 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 3.1755. Min Range: -3.1755

Max Act: 3.0021. Min Act: -0.1700

Data Index: 464910 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 3.1755. Min Range: -3.1755

Max Act: 2.9862. Min Act: -0.1700

Data Index: 1094961 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 3.1755. Min Range: -3.1755

Max Act: 2.9704. Min Act: -0.1700

Data Index: 178866 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 3.1755. Min Range: -3.1755

Max Act: 2.9704. Min Act: -0.1700

Data Index: 436165 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 3.1755. Min Range: -3.1755

Max Act: 2.9704. Min Act: -0.1700

Data Index: 1176292 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 3.1755. Min Range: -3.1755

Max Act: 2.9388. Min Act: -0.1700

Data Index: 1481581 (Python Code)

Max Activating Token Index: 869