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

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

Neuron 1902 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.7660. Min Act: -0.1700

Data Index: 886194 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.7660. Min Act: -0.1700

Data Index: 1357367 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.7190. Min Act: -0.1700

Data Index: 1100505 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.7034. Min Act: -0.1700

Data Index: 1247954 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6564. Min Act: -0.1700

Data Index: 919043 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6877. Min Act: -0.1700

Data Index: 1117484 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6721. Min Act: -0.1700

Data Index: 1145315 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6564. Min Act: -0.1700

Data Index: 560795 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6564. Min Act: -0.1700

Data Index: 688079 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6564. Min Act: -0.1700

Data Index: 1322201 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6408. Min Act: -0.1700

Data Index: 732609 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6408. Min Act: -0.1700

Data Index: 856411 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6564. Min Act: -0.1700

Data Index: 1098355 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6095. Min Act: -0.1700

Data Index: 620301 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6251. Min Act: -0.1700

Data Index: 583799 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6095. Min Act: -0.1700

Data Index: 1310542 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6251. Min Act: -0.1700

Data Index: 1333532 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6408. Min Act: -0.1700

Data Index: 589865 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6251. Min Act: -0.1700

Data Index: 738428 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 3.7660. Min Range: -3.7660

Max Act: 3.6251. Min Act: -0.1700

Data Index: 61792 (C4 (Web Text))

Max Activating Token Index: 267