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

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

Neuron 361 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.7498. Min Act: -0.1699

Data Index: 912220 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.7498. Min Act: -0.1700

Data Index: 135114 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.6873. Min Act: -0.1700

Data Index: 375040 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.6561. Min Act: -0.1700

Data Index: 1201133 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.6248. Min Act: -0.1700

Data Index: 773233 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.6248. Min Act: -0.1700

Data Index: 328700 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.5936. Min Act: -0.1698

Data Index: 1295368 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.5311. Min Act: -0.1700

Data Index: 178338 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.4998. Min Act: -0.1700

Data Index: 825206 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.4998. Min Act: -0.1700

Data Index: 71375 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.4686. Min Act: -0.1700

Data Index: 406395 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.4998. Min Act: -0.1699

Data Index: 508271 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.4998. Min Act: -0.1700

Data Index: 556587 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.4373. Min Act: -0.1700

Data Index: 321450 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.4373. Min Act: -0.1700

Data Index: 981900 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.4061. Min Act: -0.1700

Data Index: 882257 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.4686. Min Act: -0.1700

Data Index: 1283018 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.4373. Min Act: -0.1700

Data Index: 1340438 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.4061. Min Act: -0.1700

Data Index: 527984 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 5.7498. Min Range: -5.7498

Max Act: 5.4373. Min Act: -0.1700

Data Index: 755667 (C4 (Web Text))

Max Activating Token Index: 446