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

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

Neuron 1708 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.5508. Min Act: -0.1700

Data Index: 765579 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.4258. Min Act: -0.1700

Data Index: 374707 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.3946. Min Act: -0.1700

Data Index: 1333896 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.3008. Min Act: -0.1700

Data Index: 809323 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.3321. Min Act: -0.1700

Data Index: 698210 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.2383. Min Act: -0.1700

Data Index: 1025528 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.2383. Min Act: -0.1700

Data Index: 1186472 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.1758. Min Act: -0.1700

Data Index: 584269 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.2071. Min Act: -0.1700

Data Index: 907462 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.2071. Min Act: -0.1700

Data Index: 1107327 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.2071. Min Act: -0.1700

Data Index: 774940 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.1758. Min Act: -0.1700

Data Index: 695267 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.1446. Min Act: -0.1700

Data Index: 975592 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.1758. Min Act: -0.1700

Data Index: 792294 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.1446. Min Act: -0.1700

Data Index: 1341151 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.1446. Min Act: -0.1700

Data Index: 113803 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.1133. Min Act: -0.1700

Data Index: 652066 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.1133. Min Act: -0.1700

Data Index: 928668 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.1446. Min Act: -0.1700

Data Index: 399199 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 5.5508. Min Range: -5.5508

Max Act: 5.0508. Min Act: -0.1700

Data Index: 812198 (C4 (Web Text))

Max Activating Token Index: 470