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

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

Neuron 52 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1617. Min Range: -7.1617

Max Act: 7.1617. Min Act: -0.1700

Data Index: 465766 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 7.1617. Min Range: -7.1617

Max Act: 6.9117. Min Act: -0.1700

Data Index: 410864 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 7.1617. Min Range: -7.1617

Max Act: 6.8492. Min Act: -0.1700

Data Index: 1123704 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 7.1617. Min Range: -7.1617

Max Act: 6.7867. Min Act: -0.1700

Data Index: 880818 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 7.1617. Min Range: -7.1617

Max Act: 6.8805. Min Act: -0.1700

Data Index: 440240 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 7.1617. Min Range: -7.1617

Max Act: 6.7867. Min Act: -0.1700

Data Index: 1217648 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 7.1617. Min Range: -7.1617

Max Act: 6.8492. Min Act: -0.1700

Data Index: 396035 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 7.1617. Min Range: -7.1617

Max Act: 6.8180. Min Act: -0.1700

Data Index: 1332182 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 7.1617. Min Range: -7.1617

Max Act: 6.7242. Min Act: -0.1700

Data Index: 396883 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 7.1617. Min Range: -7.1617

Max Act: 6.7242. Min Act: -0.1700

Data Index: 263653 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 7.1617. Min Range: -7.1617

Max Act: 6.7555. Min Act: -0.1700

Data Index: 1193157 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 7.1617. Min Range: -7.1617

Max Act: 6.6617. Min Act: -0.1700

Data Index: 1324409 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 7.1617. Min Range: -7.1617

Max Act: 6.7242. Min Act: -0.1700

Data Index: 1345733 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 7.1617. Min Range: -7.1617

Max Act: 6.5992. Min Act: -0.1700

Data Index: 340709 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 7.1617. Min Range: -7.1617

Max Act: 6.6930. Min Act: -0.1700

Data Index: 809624 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 7.1617. Min Range: -7.1617

Max Act: 6.6930. Min Act: -0.1700

Data Index: 500285 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 7.1617. Min Range: -7.1617

Max Act: 6.6617. Min Act: -0.1700

Data Index: 918534 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 7.1617. Min Range: -7.1617

Max Act: 6.6617. Min Act: -0.1700

Data Index: 517806 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 7.1617. Min Range: -7.1617

Max Act: 6.5055. Min Act: -0.1700

Data Index: 1063134 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 7.1617. Min Range: -7.1617

Max Act: 6.5680. Min Act: -0.1699

Data Index: 103944 (C4 (Web Text))

Max Activating Token Index: 173