Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 492 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.4522. Min Act: -0.1700

Data Index: 1613635 (Python Code)

Max Activating Token Index: 508

Text #1

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.4678. Min Act: -0.1700

Data Index: 1407951 (Python Code)

Max Activating Token Index: 418

Text #2

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.3581. Min Act: -0.1700

Data Index: 1371225 (Python Code)

Max Activating Token Index: 93

Text #3

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.3581. Min Act: -0.1700

Data Index: 1538402 (Python Code)

Max Activating Token Index: 300

Text #4

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.2481. Min Act: -0.1700

Data Index: 669462 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.3424. Min Act: -0.1700

Data Index: 1600673 (Python Code)

Max Activating Token Index: 413

Text #6

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.3738. Min Act: -0.1700

Data Index: 1329603 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.2796. Min Act: -0.1700

Data Index: 735359 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.2953. Min Act: -0.1700

Data Index: 612833 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.2796. Min Act: -0.1700

Data Index: 1603042 (Python Code)

Max Activating Token Index: 48

Text #10

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.2796. Min Act: -0.1700

Data Index: 144453 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.2638. Min Act: -0.1700

Data Index: 1362645 (Python Code)

Max Activating Token Index: 535

Text #12

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.2638. Min Act: -0.1700

Data Index: 1501440 (Python Code)

Max Activating Token Index: 388

Text #13

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.2796. Min Act: -0.1700

Data Index: 1411305 (Python Code)

Max Activating Token Index: 525

Text #14

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.2638. Min Act: -0.1700

Data Index: 220367 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.2324. Min Act: -0.1700

Data Index: 1601437 (Python Code)

Max Activating Token Index: 899

Text #16

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.2324. Min Act: -0.1700

Data Index: 959092 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.2010. Min Act: -0.1700

Data Index: 1578656 (Python Code)

Max Activating Token Index: 47

Text #18

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.2324. Min Act: -0.1700

Data Index: 1367023 (Python Code)

Max Activating Token Index: 976

Text #19

Max Range: 3.4678. Min Range: -3.4678

Max Act: 3.2167. Min Act: -0.1700

Data Index: 1522479 (Python Code)

Max Activating Token Index: 509