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

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

Neuron 559 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: 3.7451. Min Range: -3.7451

Max Act: 3.7451. Min Act: -0.1700

Data Index: 1444471 (Python Code)

Max Activating Token Index: 479

Text #1

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.6825. Min Act: -0.1700

Data Index: 211306 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.6825. Min Act: -0.1700

Data Index: 117938 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.6199. Min Act: -0.1700

Data Index: 379508 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.6199. Min Act: -0.1700

Data Index: 181438 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.6512. Min Act: -0.1700

Data Index: 235352 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.6512. Min Act: -0.1700

Data Index: 1369005 (Python Code)

Max Activating Token Index: 411

Text #7

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.6512. Min Act: -0.1700

Data Index: 1437882 (Python Code)

Max Activating Token Index: 255

Text #8

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.6199. Min Act: -0.1700

Data Index: 1429584 (Python Code)

Max Activating Token Index: 358

Text #9

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.6512. Min Act: -0.1700

Data Index: 1448825 (Python Code)

Max Activating Token Index: 494

Text #10

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.6512. Min Act: -0.1700

Data Index: 1459994 (Python Code)

Max Activating Token Index: 851

Text #11

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.6199. Min Act: -0.1700

Data Index: 1484136 (Python Code)

Max Activating Token Index: 453

Text #12

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.6199. Min Act: -0.1700

Data Index: 655996 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.7138. Min Act: -0.1700

Data Index: 58532 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.6825. Min Act: -0.1700

Data Index: 1344382 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.6512. Min Act: -0.1700

Data Index: 303257 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.6512. Min Act: -0.1700

Data Index: 856688 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.6199. Min Act: -0.1700

Data Index: 824476 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.6825. Min Act: -0.1700

Data Index: 220690 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 3.7451. Min Range: -3.7451

Max Act: 3.6199. Min Act: -0.1700

Data Index: 628632 (C4 (Web Text))

Max Activating Token Index: 465