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

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

Neuron 881 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: 3.0078. Min Range: -3.0078

Max Act: 3.0005. Min Act: -0.1700

Data Index: 1303353 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.9998. Min Act: -0.1699

Data Index: 1649458 (Python Code)

Max Activating Token Index: 387

Text #2

Max Range: 3.0078. Min Range: -3.0078

Max Act: 3.0078. Min Act: -0.1700

Data Index: 1418513 (Python Code)

Max Activating Token Index: 207

Text #3

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.9670. Min Act: -0.1700

Data Index: 1541994 (Python Code)

Max Activating Token Index: 602

Text #4

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.9752. Min Act: -0.1700

Data Index: 1408665 (Python Code)

Max Activating Token Index: 440

Text #5

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.9518. Min Act: -0.1699

Data Index: 1428123 (Python Code)

Max Activating Token Index: 169

Text #6

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.9391. Min Act: -0.1700

Data Index: 455894 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.9313. Min Act: -0.1699

Data Index: 1590241 (Python Code)

Max Activating Token Index: 413

Text #8

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.9408. Min Act: -0.1700

Data Index: 1547434 (Python Code)

Max Activating Token Index: 622

Text #9

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.9381. Min Act: -0.1700

Data Index: 1370416 (Python Code)

Max Activating Token Index: 740

Text #10

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.9375. Min Act: -0.1700

Data Index: 1518683 (Python Code)

Max Activating Token Index: 614

Text #11

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.9270. Min Act: -0.1700

Data Index: 643935 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.9065. Min Act: -0.1700

Data Index: 1614374 (Python Code)

Max Activating Token Index: 513

Text #13

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.9154. Min Act: -0.1700

Data Index: 1433853 (Python Code)

Max Activating Token Index: 1004

Text #14

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.9001. Min Act: -0.1699

Data Index: 1409682 (Python Code)

Max Activating Token Index: 297

Text #15

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8899. Min Act: -0.1699

Data Index: 1560716 (Python Code)

Max Activating Token Index: 37

Text #16

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.9065. Min Act: -0.1698

Data Index: 1521320 (Python Code)

Max Activating Token Index: 341

Text #17

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.9025. Min Act: -0.1700

Data Index: 35649 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8714. Min Act: -0.1700

Data Index: 1363941 (Python Code)

Max Activating Token Index: 788

Text #19

Max Range: 3.0078. Min Range: -3.0078

Max Act: 2.8776. Min Act: -0.1700

Data Index: 1392323 (Python Code)

Max Activating Token Index: 80