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

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

Neuron 419 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3064. Min Range: -5.3064

Max Act: 5.3064. Min Act: -0.1700

Data Index: 473589 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 5.3064. Min Range: -5.3064

Max Act: 5.2439. Min Act: -0.1700

Data Index: 550898 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 5.3064. Min Range: -5.3064

Max Act: 5.2126. Min Act: -0.1700

Data Index: 306003 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 5.3064. Min Range: -5.3064

Max Act: 5.1814. Min Act: -0.1700

Data Index: 258182 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 5.3064. Min Range: -5.3064

Max Act: 5.2126. Min Act: -0.1700

Data Index: 1139494 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 5.3064. Min Range: -5.3064

Max Act: 5.1501. Min Act: -0.1700

Data Index: 207473 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 5.3064. Min Range: -5.3064

Max Act: 5.1501. Min Act: -0.1700

Data Index: 691684 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 5.3064. Min Range: -5.3064

Max Act: 5.1501. Min Act: -0.1700

Data Index: 1076567 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 5.3064. Min Range: -5.3064

Max Act: 5.1814. Min Act: -0.1700

Data Index: 299285 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 5.3064. Min Range: -5.3064

Max Act: 5.0876. Min Act: -0.1700

Data Index: 977646 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 5.3064. Min Range: -5.3064

Max Act: 5.0876. Min Act: -0.1700

Data Index: 348188 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 5.3064. Min Range: -5.3064

Max Act: 5.0876. Min Act: -0.1700

Data Index: 819789 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 5.3064. Min Range: -5.3064

Max Act: 5.0564. Min Act: -0.1700

Data Index: 1224271 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 5.3064. Min Range: -5.3064

Max Act: 5.0876. Min Act: -0.1700

Data Index: 605455 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 5.3064. Min Range: -5.3064

Max Act: 5.0876. Min Act: -0.1700

Data Index: 309962 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 5.3064. Min Range: -5.3064

Max Act: 5.0251. Min Act: -0.1700

Data Index: 215317 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 5.3064. Min Range: -5.3064

Max Act: 5.0876. Min Act: -0.1700

Data Index: 230501 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 5.3064. Min Range: -5.3064

Max Act: 4.9626. Min Act: -0.1700

Data Index: 580649 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 5.3064. Min Range: -5.3064

Max Act: 4.9939. Min Act: -0.1700

Data Index: 561468 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 5.3064. Min Range: -5.3064

Max Act: 4.9626. Min Act: -0.1700

Data Index: 719335 (C4 (Web Text))

Max Activating Token Index: 440