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

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

Neuron 280 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.8438. Min Act: -0.1700

Data Index: 292480 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.7812. Min Act: -0.1700

Data Index: 993741 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.6874. Min Act: -0.1699

Data Index: 797788 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.6247. Min Act: -0.1700

Data Index: 32547 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.5934. Min Act: -0.1700

Data Index: 1177662 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.5621. Min Act: -0.1700

Data Index: 478439 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.5621. Min Act: -0.1700

Data Index: 359085 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4995. Min Act: -0.1700

Data Index: 889735 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4368. Min Act: -0.1700

Data Index: 96949 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4681. Min Act: -0.1700

Data Index: 1326824 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4995. Min Act: -0.1700

Data Index: 397509 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4681. Min Act: -0.1700

Data Index: 155321 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4368. Min Act: -0.1700

Data Index: 628210 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4368. Min Act: -0.1700

Data Index: 638765 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4681. Min Act: -0.1700

Data Index: 471724 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4368. Min Act: -0.1700

Data Index: 439809 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4368. Min Act: -0.1700

Data Index: 350339 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4054. Min Act: -0.1700

Data Index: 1199394 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.3740. Min Act: -0.1700

Data Index: 198798 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.3740. Min Act: -0.1700

Data Index: 1294494 (C4 (Web Text))

Max Activating Token Index: 179