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

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

Neuron 1309 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.6451. Min Act: -0.1700

Data Index: 1084189 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.6138. Min Act: -0.1700

Data Index: 167464 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4885. Min Act: -0.1700

Data Index: 566373 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4728. Min Act: -0.1700

Data Index: 12560 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4728. Min Act: -0.1700

Data Index: 1323543 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4571. Min Act: -0.1700

Data Index: 116403 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4415. Min Act: -0.1700

Data Index: 626929 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4258. Min Act: -0.1700

Data Index: 159371 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.4101. Min Act: -0.1700

Data Index: 608820 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.3630. Min Act: -0.1700

Data Index: 57222 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.3630. Min Act: -0.1700

Data Index: 851586 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.3944. Min Act: -0.1700

Data Index: 1034107 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.3944. Min Act: -0.1700

Data Index: 1141480 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.3630. Min Act: -0.1700

Data Index: 577789 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.3474. Min Act: -0.1700

Data Index: 264495 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.3317. Min Act: -0.1700

Data Index: 313742 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.3474. Min Act: -0.1700

Data Index: 264335 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.3317. Min Act: -0.1700

Data Index: 48504 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.3317. Min Act: -0.1700

Data Index: 325487 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 3.6451. Min Range: -3.6451

Max Act: 3.3317. Min Act: -0.1700

Data Index: 869368 (C4 (Web Text))

Max Activating Token Index: 56