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

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

Neuron 651 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: 5.4466. Min Range: -5.4466

Max Act: 5.4466. Min Act: -0.1700

Data Index: 1271604 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 5.4466. Min Range: -5.4466

Max Act: 5.4154. Min Act: -0.1699

Data Index: 1094290 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 5.4466. Min Range: -5.4466

Max Act: 5.2591. Min Act: -0.1700

Data Index: 142635 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 5.4466. Min Range: -5.4466

Max Act: 5.2279. Min Act: -0.1700

Data Index: 44316 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 5.4466. Min Range: -5.4466

Max Act: 5.1341. Min Act: -0.1700

Data Index: 913050 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 5.4466. Min Range: -5.4466

Max Act: 5.1341. Min Act: -0.1700

Data Index: 486871 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 5.4466. Min Range: -5.4466

Max Act: 5.1341. Min Act: -0.1700

Data Index: 175039 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 5.4466. Min Range: -5.4466

Max Act: 5.1341. Min Act: -0.1700

Data Index: 891245 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 5.4466. Min Range: -5.4466

Max Act: 5.1029. Min Act: -0.1700

Data Index: 897523 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 5.4466. Min Range: -5.4466

Max Act: 5.0716. Min Act: -0.1700

Data Index: 1226134 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 5.4466. Min Range: -5.4466

Max Act: 5.0091. Min Act: -0.1700

Data Index: 515969 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 5.4466. Min Range: -5.4466

Max Act: 4.9779. Min Act: -0.1700

Data Index: 1342781 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 5.4466. Min Range: -5.4466

Max Act: 4.9154. Min Act: -0.1700

Data Index: 45138 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 5.4466. Min Range: -5.4466

Max Act: 4.9779. Min Act: -0.1700

Data Index: 374367 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 5.4466. Min Range: -5.4466

Max Act: 4.9154. Min Act: -0.1700

Data Index: 114983 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 5.4466. Min Range: -5.4466

Max Act: 4.9154. Min Act: -0.1700

Data Index: 857538 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 5.4466. Min Range: -5.4466

Max Act: 4.9154. Min Act: -0.1700

Data Index: 156422 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 5.4466. Min Range: -5.4466

Max Act: 4.8841. Min Act: -0.1700

Data Index: 576981 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 5.4466. Min Range: -5.4466

Max Act: 4.8841. Min Act: -0.1700

Data Index: 481989 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 5.4466. Min Range: -5.4466

Max Act: 4.9466. Min Act: -0.1700

Data Index: 7238 (C4 (Web Text))

Max Activating Token Index: 705