Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 467 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.5602. Min Act: -0.1700

Data Index: 1511859 (Python Code)

Max Activating Token Index: 666

Text #1

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.5132. Min Act: -0.1700

Data Index: 1609720 (Python Code)

Max Activating Token Index: 176

Text #2

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.4348. Min Act: -0.1700

Data Index: 1444598 (Python Code)

Max Activating Token Index: 338

Text #3

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.3564. Min Act: -0.1700

Data Index: 1372745 (Python Code)

Max Activating Token Index: 798

Text #4

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.3407. Min Act: -0.1700

Data Index: 1439622 (Python Code)

Max Activating Token Index: 51

Text #5

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.3407. Min Act: -0.1700

Data Index: 1584371 (Python Code)

Max Activating Token Index: 582

Text #6

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.2936. Min Act: -0.1700

Data Index: 1515691 (Python Code)

Max Activating Token Index: 22

Text #7

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.2936. Min Act: -0.1700

Data Index: 1508536 (Python Code)

Max Activating Token Index: 43

Text #8

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.2936. Min Act: -0.1700

Data Index: 1498965 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.2936. Min Act: -0.1700

Data Index: 1462402 (Python Code)

Max Activating Token Index: 587

Text #10

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.2779. Min Act: -0.1698

Data Index: 1382668 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.2779. Min Act: -0.1700

Data Index: 191845 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.2622. Min Act: -0.1700

Data Index: 1561731 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.2622. Min Act: -0.1700

Data Index: 1428913 (Python Code)

Max Activating Token Index: 776

Text #14

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.2779. Min Act: -0.1700

Data Index: 1601097 (Python Code)

Max Activating Token Index: 215

Text #15

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.2464. Min Act: -0.1700

Data Index: 1511409 (Python Code)

Max Activating Token Index: 22

Text #16

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.2464. Min Act: -0.1700

Data Index: 1509942 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.2464. Min Act: -0.1700

Data Index: 1639740 (Python Code)

Max Activating Token Index: 489

Text #18

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.2307. Min Act: -0.1700

Data Index: 1398115 (Python Code)

Max Activating Token Index: 624

Text #19

Max Range: 3.5602. Min Range: -3.5602

Max Act: 3.2150. Min Act: -0.1700

Data Index: 1422954 (Python Code)

Max Activating Token Index: 4