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

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

Neuron 1699 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: 3.8986. Min Range: -3.8986

Max Act: 3.8986. Min Act: -0.0122

Data Index: 918849 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8665. Min Act: -0.1700

Data Index: 1197000 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8511. Min Act: -0.1700

Data Index: 1271710 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.7968. Min Act: -0.1699

Data Index: 1163584 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8211. Min Act: -0.1687

Data Index: 839692 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8194. Min Act: -0.1510

Data Index: 412603 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.8126. Min Act: -0.1698

Data Index: 451968 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.7910. Min Act: -0.1700

Data Index: 881368 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.7981. Min Act: -0.1700

Data Index: 610088 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.7740. Min Act: -0.1700

Data Index: 197029 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.7293. Min Act: -0.1662

Data Index: 94357 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.7532. Min Act: -0.1690

Data Index: 1101786 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.7386. Min Act: -0.1700

Data Index: 1139907 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.7443. Min Act: -0.1699

Data Index: 1219794 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.7384. Min Act: -0.1700

Data Index: 1000020 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.7224. Min Act: -0.1698

Data Index: 550429 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.7358. Min Act: -0.1697

Data Index: 1334077 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.7189. Min Act: -0.1700

Data Index: 558010 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.6875. Min Act: -0.1699

Data Index: 370372 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 3.8986. Min Range: -3.8986

Max Act: 3.6866. Min Act: -0.1700

Data Index: 959960 (C4 (Web Text))

Max Activating Token Index: 942