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

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

Neuron 529 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.3204. Min Act: -0.1700

Data Index: 119316 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.3361. Min Act: -0.1700

Data Index: 1198818 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.3204. Min Act: -0.1700

Data Index: 930538 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.2890. Min Act: -0.1700

Data Index: 699461 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.2890. Min Act: -0.1700

Data Index: 448301 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.2890. Min Act: -0.1700

Data Index: 1327328 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.3204. Min Act: -0.1700

Data Index: 799981 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.2890. Min Act: -0.1700

Data Index: 244721 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.2733. Min Act: -0.1700

Data Index: 129506 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.2733. Min Act: -0.1700

Data Index: 973812 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.3047. Min Act: -0.1700

Data Index: 906592 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.2733. Min Act: -0.1700

Data Index: 58902 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.3047. Min Act: -0.1700

Data Index: 965642 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.2261. Min Act: -0.1700

Data Index: 181128 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.2261. Min Act: -0.1700

Data Index: 635461 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.2261. Min Act: -0.1700

Data Index: 174517 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.2418. Min Act: -0.1700

Data Index: 694233 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.2418. Min Act: -0.1700

Data Index: 900494 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.1947. Min Act: -0.1700

Data Index: 1155636 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 3.3361. Min Range: -3.3361

Max Act: 3.2418. Min Act: -0.1700

Data Index: 942443 (C4 (Web Text))

Max Activating Token Index: 665