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

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

Neuron 678 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: 3.2663. Min Range: -3.2663

Max Act: 3.2663. Min Act: -0.1700

Data Index: 949472 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 3.2663. Min Range: -3.2663

Max Act: 3.2191. Min Act: -0.1700

Data Index: 736832 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 3.2663. Min Range: -3.2663

Max Act: 3.1877. Min Act: -0.1700

Data Index: 661577 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 3.2663. Min Range: -3.2663

Max Act: 3.2348. Min Act: -0.1700

Data Index: 1136284 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 3.2663. Min Range: -3.2663

Max Act: 3.2034. Min Act: -0.1700

Data Index: 74744 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 3.2663. Min Range: -3.2663

Max Act: 3.1404. Min Act: -0.1700

Data Index: 145160 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 3.2663. Min Range: -3.2663

Max Act: 3.1089. Min Act: -0.1700

Data Index: 726213 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 3.2663. Min Range: -3.2663

Max Act: 3.0931. Min Act: -0.1700

Data Index: 60890 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 3.2663. Min Range: -3.2663

Max Act: 3.0931. Min Act: -0.1700

Data Index: 720523 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 3.2663. Min Range: -3.2663

Max Act: 3.1247. Min Act: -0.1700

Data Index: 756543 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 3.2663. Min Range: -3.2663

Max Act: 3.0774. Min Act: -0.1700

Data Index: 1102970 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 3.2663. Min Range: -3.2663

Max Act: 3.1404. Min Act: -0.1700

Data Index: 840093 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 3.2663. Min Range: -3.2663

Max Act: 3.0931. Min Act: -0.1700

Data Index: 1155992 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 3.2663. Min Range: -3.2663

Max Act: 3.0774. Min Act: -0.1700

Data Index: 766640 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 3.2663. Min Range: -3.2663

Max Act: 3.0458. Min Act: -0.1700

Data Index: 1068248 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 3.2663. Min Range: -3.2663

Max Act: 3.0458. Min Act: -0.1700

Data Index: 971909 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 3.2663. Min Range: -3.2663

Max Act: 3.0616. Min Act: -0.1700

Data Index: 27573 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 3.2663. Min Range: -3.2663

Max Act: 2.9984. Min Act: -0.1700

Data Index: 1107380 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 3.2663. Min Range: -3.2663

Max Act: 3.0300. Min Act: -0.1700

Data Index: 1070950 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 3.2663. Min Range: -3.2663

Max Act: 3.0300. Min Act: -0.1700

Data Index: 986335 (C4 (Web Text))

Max Activating Token Index: 116