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

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

Neuron 146 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.1645. Min Act: -0.1700

Data Index: 333859 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.1488. Min Act: -0.1700

Data Index: 907517 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.1173. Min Act: -0.1700

Data Index: 1111953 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.1173. Min Act: -0.1700

Data Index: 713828 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.1015. Min Act: -0.1700

Data Index: 544124 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.1173. Min Act: -0.1700

Data Index: 1238432 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.0858. Min Act: -0.1700

Data Index: 1201168 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.1173. Min Act: -0.1700

Data Index: 952012 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.0700. Min Act: -0.1700

Data Index: 737849 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.0700. Min Act: -0.1700

Data Index: 257247 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.0542. Min Act: -0.1700

Data Index: 165566 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.0542. Min Act: -0.1700

Data Index: 799559 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.0384. Min Act: -0.1700

Data Index: 387607 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.0384. Min Act: -0.1700

Data Index: 1323494 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.0068. Min Act: -0.1700

Data Index: 752744 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.0226. Min Act: -0.1700

Data Index: 427000 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.0226. Min Act: -0.1700

Data Index: 617405 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.0226. Min Act: -0.1700

Data Index: 759888 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.0068. Min Act: -0.1700

Data Index: 513275 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 3.1645. Min Range: -3.1645

Max Act: 3.0068. Min Act: -0.1700

Data Index: 815853 (C4 (Web Text))

Max Activating Token Index: 982