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

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

Neuron 1009 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: 5.3855. Min Range: -5.3855

Max Act: 5.3543. Min Act: -0.1700

Data Index: 740575 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 5.3855. Min Range: -5.3855

Max Act: 5.3543. Min Act: -0.1700

Data Index: 15919 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 5.3855. Min Range: -5.3855

Max Act: 5.3543. Min Act: -0.1700

Data Index: 861172 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 5.3855. Min Range: -5.3855

Max Act: 5.3543. Min Act: -0.1700

Data Index: 1151634 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 5.3855. Min Range: -5.3855

Max Act: 5.3230. Min Act: -0.1700

Data Index: 946994 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 5.3855. Min Range: -5.3855

Max Act: 5.2918. Min Act: -0.1700

Data Index: 303282 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 5.3855. Min Range: -5.3855

Max Act: 5.3543. Min Act: -0.1700

Data Index: 929801 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 5.3855. Min Range: -5.3855

Max Act: 5.3230. Min Act: -0.1700

Data Index: 866299 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 5.3855. Min Range: -5.3855

Max Act: 5.3543. Min Act: -0.1700

Data Index: 519339 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 5.3855. Min Range: -5.3855

Max Act: 5.2293. Min Act: -0.1700

Data Index: 463 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 5.3855. Min Range: -5.3855

Max Act: 5.3855. Min Act: -0.1700

Data Index: 463014 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 5.3855. Min Range: -5.3855

Max Act: 5.2918. Min Act: -0.1700

Data Index: 253411 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 5.3855. Min Range: -5.3855

Max Act: 5.2918. Min Act: -0.1700

Data Index: 183241 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 5.3855. Min Range: -5.3855

Max Act: 5.2293. Min Act: -0.1700

Data Index: 125049 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 5.3855. Min Range: -5.3855

Max Act: 5.1668. Min Act: -0.1700

Data Index: 1174006 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 5.3855. Min Range: -5.3855

Max Act: 5.2918. Min Act: -0.1700

Data Index: 102244 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 5.3855. Min Range: -5.3855

Max Act: 5.3230. Min Act: -0.1700

Data Index: 889140 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 5.3855. Min Range: -5.3855

Max Act: 5.2605. Min Act: -0.1700

Data Index: 1001022 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 5.3855. Min Range: -5.3855

Max Act: 5.2605. Min Act: -0.1700

Data Index: 705830 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 5.3855. Min Range: -5.3855

Max Act: 5.2918. Min Act: -0.1700

Data Index: 1137783 (C4 (Web Text))

Max Activating Token Index: 464