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

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

Neuron 59 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: 3.2807. Min Range: -3.2807

Max Act: 3.2807. Min Act: -0.1700

Data Index: 1351646 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.2650. Min Act: -0.1700

Data Index: 502219 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.2179. Min Act: -0.1700

Data Index: 945315 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.1392. Min Act: -0.1700

Data Index: 333762 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.1234. Min Act: -0.1700

Data Index: 142625 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.1392. Min Act: -0.1700

Data Index: 362839 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.1234. Min Act: -0.1700

Data Index: 1127849 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.1076. Min Act: -0.1700

Data Index: 1277297 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.1234. Min Act: -0.1700

Data Index: 804051 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.1076. Min Act: -0.1700

Data Index: 851903 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0919. Min Act: -0.1700

Data Index: 1191970 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0919. Min Act: -0.1699

Data Index: 686256 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0761. Min Act: -0.1700

Data Index: 423376 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0761. Min Act: -0.1700

Data Index: 10515 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0761. Min Act: -0.1700

Data Index: 949090 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0603. Min Act: -0.1700

Data Index: 193409 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0603. Min Act: -0.1700

Data Index: 679657 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0445. Min Act: -0.1700

Data Index: 765541 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0445. Min Act: -0.1700

Data Index: 381203 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0287. Min Act: -0.1700

Data Index: 1077837 (C4 (Web Text))

Max Activating Token Index: 10