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

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

Neuron 673 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.6498. Min Act: -0.1700

Data Index: 14179 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.6498. Min Act: -0.1700

Data Index: 1167155 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.5560. Min Act: -0.1700

Data Index: 373839 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.5873. Min Act: -0.1700

Data Index: 99831 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.5560. Min Act: -0.1700

Data Index: 1237171 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.5873. Min Act: -0.1700

Data Index: 140630 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.4935. Min Act: -0.1700

Data Index: 764545 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.5248. Min Act: -0.1700

Data Index: 875674 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.4935. Min Act: -0.1700

Data Index: 61024 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.5560. Min Act: -0.1700

Data Index: 1329238 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.5248. Min Act: -0.1700

Data Index: 700000 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.5560. Min Act: -0.1700

Data Index: 646749 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.5560. Min Act: -0.1700

Data Index: 1213969 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.5248. Min Act: -0.1700

Data Index: 640691 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.5248. Min Act: -0.1700

Data Index: 412679 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.5248. Min Act: -0.1700

Data Index: 402157 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.4935. Min Act: -0.1700

Data Index: 941949 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.4623. Min Act: -0.1700

Data Index: 257937 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.4935. Min Act: -0.1700

Data Index: 222951 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 5.6498. Min Range: -5.6498

Max Act: 5.4935. Min Act: -0.1700

Data Index: 390588 (C4 (Web Text))

Max Activating Token Index: 330