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

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

Neuron 1674 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: 2.5260. Min Range: -2.5260

Max Act: 2.5219. Min Act: -0.1679

Data Index: 686336 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.5260. Min Act: -0.1700

Data Index: 1173093 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.4564. Min Act: -0.1700

Data Index: 1515691 (Python Code)

Max Activating Token Index: 678

Text #3

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.4599. Min Act: -0.1699

Data Index: 1445294 (Python Code)

Max Activating Token Index: 662

Text #4

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.4132. Min Act: -0.1696

Data Index: 1438486 (Python Code)

Max Activating Token Index: 133

Text #5

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.4220. Min Act: -0.1700

Data Index: 1342976 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.4288. Min Act: -0.1700

Data Index: 563568 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.4143. Min Act: -0.1700

Data Index: 1393106 (Python Code)

Max Activating Token Index: 756

Text #8

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.4137. Min Act: -0.1699

Data Index: 1360387 (Python Code)

Max Activating Token Index: 786

Text #9

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.3592. Min Act: -0.1700

Data Index: 1318774 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.3596. Min Act: -0.1700

Data Index: 1596363 (Python Code)

Max Activating Token Index: 833

Text #11

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.3602. Min Act: -0.1699

Data Index: 1578904 (Python Code)

Max Activating Token Index: 743

Text #12

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.3635. Min Act: -0.1700

Data Index: 1480411 (Python Code)

Max Activating Token Index: 1012

Text #13

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.3609. Min Act: -0.1700

Data Index: 138929 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.3495. Min Act: -0.1700

Data Index: 1413684 (Python Code)

Max Activating Token Index: 597

Text #15

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.3416. Min Act: -0.1696

Data Index: 1380272 (Python Code)

Max Activating Token Index: 684

Text #16

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.3428. Min Act: -0.1700

Data Index: 1640667 (Python Code)

Max Activating Token Index: 764

Text #17

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.3353. Min Act: -0.1700

Data Index: 1640961 (Python Code)

Max Activating Token Index: 887

Text #18

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.3221. Min Act: -0.1700

Data Index: 1426190 (Python Code)

Max Activating Token Index: 733

Text #19

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.3371. Min Act: -0.1700

Data Index: 1407310 (Python Code)

Max Activating Token Index: 1022