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

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

Neuron 161 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.6873. Min Act: -0.1700

Data Index: 132195 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.6873. Min Act: -0.1700

Data Index: 1099401 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.4681. Min Act: -0.1700

Data Index: 1020224 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.4210. Min Act: -0.1700

Data Index: 1064235 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.4367. Min Act: -0.1700

Data Index: 821000 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.3897. Min Act: -0.1700

Data Index: 1249632 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.3583. Min Act: -0.1700

Data Index: 974840 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.3897. Min Act: -0.1700

Data Index: 279566 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.4524. Min Act: -0.1700

Data Index: 72421 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.3897. Min Act: -0.1700

Data Index: 1027869 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.4054. Min Act: -0.1700

Data Index: 238663 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.3897. Min Act: -0.1700

Data Index: 955297 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.3897. Min Act: -0.1700

Data Index: 979889 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.3269. Min Act: -0.1700

Data Index: 67819 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.2641. Min Act: -0.1700

Data Index: 1261502 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.3740. Min Act: -0.1700

Data Index: 481004 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.3740. Min Act: -0.1700

Data Index: 1329504 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.3740. Min Act: -0.1700

Data Index: 289393 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.3583. Min Act: -0.1700

Data Index: 23247 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.3426. Min Act: -0.1700

Data Index: 1048291 (C4 (Web Text))

Max Activating Token Index: 558