Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 129 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.5179. Min Range: -4.5179

Max Act: 4.5179. Min Act: -0.1700

Data Index: 238948 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 4.5179. Min Range: -4.5179

Max Act: 4.3000. Min Act: -0.1700

Data Index: 61997 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 4.5179. Min Range: -4.5179

Max Act: 4.2018. Min Act: -0.1700

Data Index: 740100 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 4.5179. Min Range: -4.5179

Max Act: 3.9184. Min Act: -0.1700

Data Index: 345352 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 4.5179. Min Range: -4.5179

Max Act: 3.8165. Min Act: -0.1700

Data Index: 1591743 (Python Code)

Max Activating Token Index: 996

Text #5

Max Range: 4.5179. Min Range: -4.5179

Max Act: 3.8072. Min Act: -0.1700

Data Index: 1185842 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 4.5179. Min Range: -4.5179

Max Act: 3.7703. Min Act: -0.1700

Data Index: 1374172 (Python Code)

Max Activating Token Index: 858

Text #7

Max Range: 4.5179. Min Range: -4.5179

Max Act: 3.7575. Min Act: -0.1700

Data Index: 1462701 (Python Code)

Max Activating Token Index: 385

Text #8

Max Range: 4.5179. Min Range: -4.5179

Max Act: 3.7284. Min Act: -0.1699

Data Index: 888177 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 4.5179. Min Range: -4.5179

Max Act: 3.6658. Min Act: -0.1700

Data Index: 1027226 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 4.5179. Min Range: -4.5179

Max Act: 3.6400. Min Act: -0.1700

Data Index: 1454954 (Python Code)

Max Activating Token Index: 875

Text #11

Max Range: 4.5179. Min Range: -4.5179

Max Act: 3.6031. Min Act: -0.1700

Data Index: 1405970 (Python Code)

Max Activating Token Index: 443

Text #12

Max Range: 4.5179. Min Range: -4.5179

Max Act: 3.6118. Min Act: -0.1700

Data Index: 295741 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 4.5179. Min Range: -4.5179

Max Act: 3.6212. Min Act: -0.1700

Data Index: 332201 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 4.5179. Min Range: -4.5179

Max Act: 3.6078. Min Act: -0.1699

Data Index: 43922 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 4.5179. Min Range: -4.5179

Max Act: 3.5632. Min Act: -0.1699

Data Index: 445544 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 4.5179. Min Range: -4.5179

Max Act: 3.5757. Min Act: -0.1698

Data Index: 751149 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 4.5179. Min Range: -4.5179

Max Act: 3.5775. Min Act: -0.1699

Data Index: 1320160 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 4.5179. Min Range: -4.5179

Max Act: 3.5645. Min Act: -0.1698

Data Index: 635973 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 4.5179. Min Range: -4.5179

Max Act: 3.5652. Min Act: -0.1699

Data Index: 1417499 (Python Code)

Max Activating Token Index: 692