Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 504 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.6283. Min Act: -0.1700

Data Index: 1413169 (Python Code)

Max Activating Token Index: 680

Text #1

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.5346. Min Act: -0.1700

Data Index: 1488847 (Python Code)

Max Activating Token Index: 241

Text #2

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.5658. Min Act: -0.1700

Data Index: 1590808 (Python Code)

Max Activating Token Index: 205

Text #3

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.5033. Min Act: -0.1700

Data Index: 1425505 (Python Code)

Max Activating Token Index: 638

Text #4

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.4721. Min Act: -0.1700

Data Index: 1441154 (Python Code)

Max Activating Token Index: 379

Text #5

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.4721. Min Act: -0.1698

Data Index: 1622530 (Python Code)

Max Activating Token Index: 317

Text #6

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.4721. Min Act: -0.1700

Data Index: 1570902 (Python Code)

Max Activating Token Index: 590

Text #7

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.4408. Min Act: -0.1700

Data Index: 1525122 (Python Code)

Max Activating Token Index: 137

Text #8

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.4096. Min Act: -0.1700

Data Index: 1396946 (Python Code)

Max Activating Token Index: 465

Text #9

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.4408. Min Act: -0.1700

Data Index: 1601154 (Python Code)

Max Activating Token Index: 603

Text #10

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.4096. Min Act: -0.1686

Data Index: 1489609 (Python Code)

Max Activating Token Index: 820

Text #11

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.3783. Min Act: -0.1700

Data Index: 1471225 (Python Code)

Max Activating Token Index: 261

Text #12

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.3783. Min Act: -0.1700

Data Index: 1570620 (Python Code)

Max Activating Token Index: 89

Text #13

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.3158. Min Act: -0.1700

Data Index: 1508882 (Python Code)

Max Activating Token Index: 516

Text #14

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.3158. Min Act: -0.1700

Data Index: 1626497 (Python Code)

Max Activating Token Index: 394

Text #15

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.3783. Min Act: -0.1700

Data Index: 1448246 (Python Code)

Max Activating Token Index: 359

Text #16

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.3158. Min Act: -0.1700

Data Index: 1422433 (Python Code)

Max Activating Token Index: 562

Text #17

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.3471. Min Act: -0.1699

Data Index: 1436411 (Python Code)

Max Activating Token Index: 547

Text #18

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.3783. Min Act: -0.1699

Data Index: 117889 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 5.6283. Min Range: -5.6283

Max Act: 5.2533. Min Act: -0.1700

Data Index: 1463816 (Python Code)

Max Activating Token Index: 509