Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1627 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.7541. Min Act: -0.1687

Data Index: 929733 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.7560. Min Act: -0.0993

Data Index: 1268287 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.6774. Min Act: -0.1699

Data Index: 1351753 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.6532. Min Act: -0.1696

Data Index: 849244 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.6533. Min Act: -0.0993

Data Index: 651989 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.6579. Min Act: -0.0993

Data Index: 659683 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.6356. Min Act: -0.1240

Data Index: 733366 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.6293. Min Act: -0.1669

Data Index: 1005370 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5862. Min Act: -0.1696

Data Index: 430999 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.6178. Min Act: -0.1695

Data Index: 453229 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.6118. Min Act: -0.0993

Data Index: 885851 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.6097. Min Act: -0.1651

Data Index: 651193 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.6113. Min Act: -0.1687

Data Index: 631691 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5702. Min Act: -0.1697

Data Index: 413756 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5543. Min Act: -0.1699

Data Index: 1031998 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5534. Min Act: -0.1694

Data Index: 468259 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5821. Min Act: -0.0993

Data Index: 992812 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5285. Min Act: -0.1681

Data Index: 537380 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5246. Min Act: -0.1686

Data Index: 888304 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5557. Min Act: -0.1696

Data Index: 577954 (C4 (Web Text))

Max Activating Token Index: 860