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

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

Neuron 1065 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.3335. Min Act: -0.1700

Data Index: 391894 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.2864. Min Act: -0.1700

Data Index: 1214024 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.2392. Min Act: -0.1700

Data Index: 133737 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.2392. Min Act: -0.1700

Data Index: 466133 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.2550. Min Act: -0.1700

Data Index: 1025939 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.2235. Min Act: -0.1700

Data Index: 617805 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.1606. Min Act: -0.1700

Data Index: 1279904 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.1921. Min Act: -0.1700

Data Index: 814885 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.1763. Min Act: -0.1700

Data Index: 209051 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.1921. Min Act: -0.1700

Data Index: 62192 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.1606. Min Act: -0.1700

Data Index: 1180404 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.1133. Min Act: -0.1700

Data Index: 443336 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.1606. Min Act: -0.1700

Data Index: 666972 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.1606. Min Act: -0.1700

Data Index: 297580 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.1448. Min Act: -0.1700

Data Index: 25891 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.1606. Min Act: -0.1700

Data Index: 575994 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.1133. Min Act: -0.1700

Data Index: 657479 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.1606. Min Act: -0.1700

Data Index: 605312 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.1291. Min Act: -0.1700

Data Index: 962831 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 3.3335. Min Range: -3.3335

Max Act: 3.1133. Min Act: -0.1700

Data Index: 938078 (C4 (Web Text))

Max Activating Token Index: 481