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

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

Neuron 265 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: 3.8194. Min Range: -3.8194

Max Act: 3.8194. Min Act: -0.1700

Data Index: 313365 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.6942. Min Act: -0.1700

Data Index: 453859 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.6942. Min Act: -0.1700

Data Index: 187002 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.6316. Min Act: -0.1700

Data Index: 624850 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.5376. Min Act: -0.1700

Data Index: 322815 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.6003. Min Act: -0.1700

Data Index: 807030 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.5690. Min Act: -0.1700

Data Index: 835662 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.5376. Min Act: -0.1700

Data Index: 573970 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.5063. Min Act: -0.1700

Data Index: 177712 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4750. Min Act: -0.1700

Data Index: 1114627 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4436. Min Act: -0.1700

Data Index: 754388 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4750. Min Act: -0.1700

Data Index: 841599 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.5063. Min Act: -0.1700

Data Index: 507889 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.5063. Min Act: -0.1700

Data Index: 303799 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4750. Min Act: -0.1700

Data Index: 467352 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4750. Min Act: -0.1700

Data Index: 863084 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4436. Min Act: -0.1700

Data Index: 393588 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4436. Min Act: -0.1700

Data Index: 825971 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4750. Min Act: -0.1700

Data Index: 128279 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4750. Min Act: -0.1700

Data Index: 791001 (C4 (Web Text))

Max Activating Token Index: 15