Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 767 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.0457. Min Range: -7.0457

Max Act: 7.0457. Min Act: -0.1700

Data Index: 1021946 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 7.0457. Min Range: -7.0457

Max Act: 6.9207. Min Act: -0.1700

Data Index: 272287 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 7.0457. Min Range: -7.0457

Max Act: 6.9520. Min Act: -0.1700

Data Index: 1346465 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 7.0457. Min Range: -7.0457

Max Act: 6.9207. Min Act: -0.1700

Data Index: 192084 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 7.0457. Min Range: -7.0457

Max Act: 6.9832. Min Act: -0.1700

Data Index: 453388 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 7.0457. Min Range: -7.0457

Max Act: 6.9832. Min Act: -0.1700

Data Index: 603057 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 7.0457. Min Range: -7.0457

Max Act: 6.9520. Min Act: -0.1700

Data Index: 288218 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 7.0457. Min Range: -7.0457

Max Act: 6.8895. Min Act: -0.1700

Data Index: 259020 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 7.0457. Min Range: -7.0457

Max Act: 6.9207. Min Act: -0.1700

Data Index: 607371 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 7.0457. Min Range: -7.0457

Max Act: 6.9207. Min Act: -0.1700

Data Index: 437328 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 7.0457. Min Range: -7.0457

Max Act: 6.8582. Min Act: -0.1700

Data Index: 198413 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 7.0457. Min Range: -7.0457

Max Act: 6.8270. Min Act: -0.1700

Data Index: 416244 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 7.0457. Min Range: -7.0457

Max Act: 6.8582. Min Act: -0.1700

Data Index: 1076549 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 7.0457. Min Range: -7.0457

Max Act: 6.9207. Min Act: -0.1700

Data Index: 357688 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 7.0457. Min Range: -7.0457

Max Act: 6.8582. Min Act: -0.1700

Data Index: 225812 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 7.0457. Min Range: -7.0457

Max Act: 6.8582. Min Act: -0.1700

Data Index: 381258 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 7.0457. Min Range: -7.0457

Max Act: 6.8270. Min Act: -0.1700

Data Index: 734507 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 7.0457. Min Range: -7.0457

Max Act: 6.7957. Min Act: -0.1700

Data Index: 632324 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 7.0457. Min Range: -7.0457

Max Act: 6.7645. Min Act: -0.1700

Data Index: 623265 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 7.0457. Min Range: -7.0457

Max Act: 6.7645. Min Act: -0.1700

Data Index: 1403836 (Python Code)

Max Activating Token Index: 302