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

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

Neuron 79 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: 3.6847. Min Range: -3.6847

Max Act: 3.6847. Min Act: -0.1700

Data Index: 1542510 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.5468. Min Act: -0.1700

Data Index: 1652768 (Python Code)

Max Activating Token Index: 59

Text #2

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4709. Min Act: -0.1700

Data Index: 1580976 (Python Code)

Max Activating Token Index: 676

Text #3

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4770. Min Act: -0.1699

Data Index: 1490602 (Python Code)

Max Activating Token Index: 130

Text #4

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4627. Min Act: -0.1700

Data Index: 1037814 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4776. Min Act: -0.1699

Data Index: 1475082 (Python Code)

Max Activating Token Index: 873

Text #6

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4454. Min Act: -0.1699

Data Index: 1295965 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.4080. Min Act: -0.1700

Data Index: 1649302 (Python Code)

Max Activating Token Index: 399

Text #8

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.3505. Min Act: -0.1699

Data Index: 1655242 (Python Code)

Max Activating Token Index: 353

Text #9

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.3290. Min Act: -0.1700

Data Index: 178081 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.3219. Min Act: -0.1700

Data Index: 1649672 (Python Code)

Max Activating Token Index: 464

Text #11

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.3130. Min Act: -0.1700

Data Index: 1549322 (Python Code)

Max Activating Token Index: 992

Text #12

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.3032. Min Act: -0.1700

Data Index: 1443480 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.3221. Min Act: -0.1700

Data Index: 1387620 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.2771. Min Act: -0.1700

Data Index: 1513049 (Python Code)

Max Activating Token Index: 714

Text #15

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.2728. Min Act: -0.1700

Data Index: 1446024 (Python Code)

Max Activating Token Index: 401

Text #16

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.2664. Min Act: -0.1700

Data Index: 1538933 (Python Code)

Max Activating Token Index: 600

Text #17

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.2664. Min Act: -0.1700

Data Index: 1596304 (Python Code)

Max Activating Token Index: 75

Text #18

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.2716. Min Act: -0.1700

Data Index: 1222312 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 3.6847. Min Range: -3.6847

Max Act: 3.2491. Min Act: -0.1699

Data Index: 81603 (C4 (Web Text))

Max Activating Token Index: 190