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

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

Neuron 1856 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: 3.5306. Min Range: -3.5306

Max Act: 3.5306. Min Act: -0.1700

Data Index: 389102 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 3.5306. Min Range: -3.5306

Max Act: 3.4522. Min Act: -0.1700

Data Index: 1109410 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 3.5306. Min Range: -3.5306

Max Act: 3.3424. Min Act: -0.1700

Data Index: 1119567 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 3.5306. Min Range: -3.5306

Max Act: 3.3424. Min Act: -0.1700

Data Index: 501218 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 3.5306. Min Range: -3.5306

Max Act: 3.3267. Min Act: -0.1700

Data Index: 40592 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 3.5306. Min Range: -3.5306

Max Act: 3.2953. Min Act: -0.1700

Data Index: 1047793 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 3.5306. Min Range: -3.5306

Max Act: 3.3110. Min Act: -0.1700

Data Index: 806044 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 3.5306. Min Range: -3.5306

Max Act: 3.2796. Min Act: -0.1700

Data Index: 1173319 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 3.5306. Min Range: -3.5306

Max Act: 3.2324. Min Act: -0.1700

Data Index: 216797 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 3.5306. Min Range: -3.5306

Max Act: 3.2324. Min Act: -0.1700

Data Index: 1346908 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 3.5306. Min Range: -3.5306

Max Act: 3.2324. Min Act: -0.1700

Data Index: 803836 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 3.5306. Min Range: -3.5306

Max Act: 3.2324. Min Act: -0.1700

Data Index: 842607 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 3.5306. Min Range: -3.5306

Max Act: 3.2324. Min Act: -0.1700

Data Index: 1167990 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 3.5306. Min Range: -3.5306

Max Act: 3.2482. Min Act: -0.1700

Data Index: 1276600 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 3.5306. Min Range: -3.5306

Max Act: 3.1538. Min Act: -0.1700

Data Index: 131852 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 3.5306. Min Range: -3.5306

Max Act: 3.1853. Min Act: -0.1700

Data Index: 97359 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 3.5306. Min Range: -3.5306

Max Act: 3.1853. Min Act: -0.1700

Data Index: 1329035 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 3.5306. Min Range: -3.5306

Max Act: 3.2167. Min Act: -0.1700

Data Index: 138149 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 3.5306. Min Range: -3.5306

Max Act: 3.2010. Min Act: -0.1700

Data Index: 1079743 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 3.5306. Min Range: -3.5306

Max Act: 3.2010. Min Act: -0.1700

Data Index: 505104 (C4 (Web Text))

Max Activating Token Index: 687