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

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

Neuron 287 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: 3.6973. Min Range: -3.6973

Max Act: 3.6973. Min Act: -0.1700

Data Index: 695818 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 3.6973. Min Range: -3.6973

Max Act: 3.6370. Min Act: -0.1700

Data Index: 743888 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 3.6973. Min Range: -3.6973

Max Act: 3.6035. Min Act: -0.1700

Data Index: 504749 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 3.6973. Min Range: -3.6973

Max Act: 3.5827. Min Act: -0.1700

Data Index: 531027 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 3.6973. Min Range: -3.6973

Max Act: 3.5788. Min Act: -0.1700

Data Index: 323835 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 3.6973. Min Range: -3.6973

Max Act: 3.5781. Min Act: -0.1700

Data Index: 663464 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 3.6973. Min Range: -3.6973

Max Act: 3.5729. Min Act: -0.1700

Data Index: 1284337 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 3.6973. Min Range: -3.6973

Max Act: 3.5887. Min Act: -0.1700

Data Index: 494382 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 3.6973. Min Range: -3.6973

Max Act: 3.5586. Min Act: -0.1700

Data Index: 1153719 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 3.6973. Min Range: -3.6973

Max Act: 3.5714. Min Act: -0.1700

Data Index: 1034772 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 3.6973. Min Range: -3.6973

Max Act: 3.5601. Min Act: -0.1700

Data Index: 1357200 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 3.6973. Min Range: -3.6973

Max Act: 3.5542. Min Act: -0.1700

Data Index: 1222221 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 3.6973. Min Range: -3.6973

Max Act: 3.5591. Min Act: -0.1700

Data Index: 1351097 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 3.6973. Min Range: -3.6973

Max Act: 3.5399. Min Act: -0.1700

Data Index: 399218 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 3.6973. Min Range: -3.6973

Max Act: 3.5481. Min Act: -0.1700

Data Index: 286430 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 3.6973. Min Range: -3.6973

Max Act: 3.5553. Min Act: -0.1700

Data Index: 150431 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 3.6973. Min Range: -3.6973

Max Act: 3.5503. Min Act: -0.1700

Data Index: 232826 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 3.6973. Min Range: -3.6973

Max Act: 3.5437. Min Act: -0.1700

Data Index: 1063103 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 3.6973. Min Range: -3.6973

Max Act: 3.5242. Min Act: -0.1700

Data Index: 1322446 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 3.6973. Min Range: -3.6973

Max Act: 3.5371. Min Act: -0.1700

Data Index: 1146481 (C4 (Web Text))

Max Activating Token Index: 726