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

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

Neuron 23 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: 6.3425. Min Range: -6.3425

Max Act: 6.3425. Min Act: -0.1700

Data Index: 361842 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 6.3425. Min Range: -6.3425

Max Act: 6.1983. Min Act: -0.1700

Data Index: 916791 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 6.3425. Min Range: -6.3425

Max Act: 6.1295. Min Act: -0.1700

Data Index: 703562 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 6.3425. Min Range: -6.3425

Max Act: 6.1442. Min Act: -0.1693

Data Index: 273303 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 6.3425. Min Range: -6.3425

Max Act: 6.1194. Min Act: -0.1700

Data Index: 1123148 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 6.3425. Min Range: -6.3425

Max Act: 6.1248. Min Act: -0.1700

Data Index: 1211569 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 6.3425. Min Range: -6.3425

Max Act: 6.0823. Min Act: -0.1700

Data Index: 1189591 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 6.3425. Min Range: -6.3425

Max Act: 6.0177. Min Act: -0.1700

Data Index: 72160 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 6.3425. Min Range: -6.3425

Max Act: 6.0003. Min Act: -0.1700

Data Index: 1345528 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 6.3425. Min Range: -6.3425

Max Act: 6.0121. Min Act: -0.1698

Data Index: 764858 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 6.3425. Min Range: -6.3425

Max Act: 6.0364. Min Act: -0.1700

Data Index: 1217852 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 6.3425. Min Range: -6.3425

Max Act: 6.0248. Min Act: -0.1698

Data Index: 1057886 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 6.3425. Min Range: -6.3425

Max Act: 5.9547. Min Act: -0.1700

Data Index: 245505 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 6.3425. Min Range: -6.3425

Max Act: 5.9623. Min Act: -0.1697

Data Index: 471305 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 6.3425. Min Range: -6.3425

Max Act: 5.9755. Min Act: -0.1700

Data Index: 303864 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 6.3425. Min Range: -6.3425

Max Act: 5.9885. Min Act: -0.1700

Data Index: 460330 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 6.3425. Min Range: -6.3425

Max Act: 6.0094. Min Act: -0.1700

Data Index: 830009 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 6.3425. Min Range: -6.3425

Max Act: 5.9590. Min Act: -0.1700

Data Index: 123455 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 6.3425. Min Range: -6.3425

Max Act: 5.9900. Min Act: -0.1700

Data Index: 516434 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 6.3425. Min Range: -6.3425

Max Act: 5.9916. Min Act: -0.1700

Data Index: 199303 (C4 (Web Text))

Max Activating Token Index: 20