Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 199 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.1229. Min Range: -3.1229

Max Act: 3.1229. Min Act: -0.1699

Data Index: 1262669 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 3.1229. Min Range: -3.1229

Max Act: 3.1209. Min Act: -0.1700

Data Index: 1617442 (Python Code)

Max Activating Token Index: 145

Text #2

Max Range: 3.1229. Min Range: -3.1229

Max Act: 3.1209. Min Act: -0.1700

Data Index: 1369815 (Python Code)

Max Activating Token Index: 851

Text #3

Max Range: 3.1229. Min Range: -3.1229

Max Act: 3.0948. Min Act: -0.1699

Data Index: 1506663 (Python Code)

Max Activating Token Index: 80

Text #4

Max Range: 3.1229. Min Range: -3.1229

Max Act: 3.0803. Min Act: -0.1700

Data Index: 842835 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 3.1229. Min Range: -3.1229

Max Act: 3.0669. Min Act: -0.1693

Data Index: 1494497 (Python Code)

Max Activating Token Index: 230

Text #6

Max Range: 3.1229. Min Range: -3.1229

Max Act: 3.0654. Min Act: -0.1700

Data Index: 132933 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 3.1229. Min Range: -3.1229

Max Act: 3.0550. Min Act: -0.1700

Data Index: 434257 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 3.1229. Min Range: -3.1229

Max Act: 3.0607. Min Act: -0.1700

Data Index: 1119895 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 3.1229. Min Range: -3.1229

Max Act: 3.0561. Min Act: -0.1698

Data Index: 258820 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 3.1229. Min Range: -3.1229

Max Act: 3.0356. Min Act: -0.1700

Data Index: 528667 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 3.1229. Min Range: -3.1229

Max Act: 3.0260. Min Act: -0.1700

Data Index: 902197 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 3.1229. Min Range: -3.1229

Max Act: 3.0279. Min Act: -0.1700

Data Index: 396176 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 3.1229. Min Range: -3.1229

Max Act: 3.0268. Min Act: -0.1700

Data Index: 439016 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 3.1229. Min Range: -3.1229

Max Act: 3.0120. Min Act: -0.1700

Data Index: 933559 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 3.1229. Min Range: -3.1229

Max Act: 3.0007. Min Act: -0.1692

Data Index: 1416830 (Python Code)

Max Activating Token Index: 708

Text #16

Max Range: 3.1229. Min Range: -3.1229

Max Act: 3.0086. Min Act: -0.1560

Data Index: 1406090 (Python Code)

Max Activating Token Index: 233

Text #17

Max Range: 3.1229. Min Range: -3.1229

Max Act: 3.0121. Min Act: -0.1560

Data Index: 835447 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 3.1229. Min Range: -3.1229

Max Act: 3.0081. Min Act: -0.1700

Data Index: 571970 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 3.1229. Min Range: -3.1229

Max Act: 2.9943. Min Act: -0.1698

Data Index: 1503248 (Python Code)

Max Activating Token Index: 923