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

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

Neuron 473 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: 3.3370. Min Range: -3.3370

Max Act: 3.3370. Min Act: -0.1700

Data Index: 1530410 (Python Code)

Max Activating Token Index: 728

Text #1

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.2651. Min Act: -0.1700

Data Index: 356936 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.2393. Min Act: -0.1700

Data Index: 43121 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.1852. Min Act: -0.1700

Data Index: 511371 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.1607. Min Act: -0.1700

Data Index: 1137845 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.1330. Min Act: -0.1700

Data Index: 195615 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.1399. Min Act: -0.1700

Data Index: 965511 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.1267. Min Act: -0.1700

Data Index: 892269 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.1284. Min Act: -0.1700

Data Index: 1137333 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.1235. Min Act: -0.1700

Data Index: 106219 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.1231. Min Act: -0.1700

Data Index: 1314956 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.1006. Min Act: -0.1700

Data Index: 1053573 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.0939. Min Act: -0.1700

Data Index: 947843 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.1019. Min Act: -0.1700

Data Index: 229232 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.1019. Min Act: -0.1700

Data Index: 727253 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.0981. Min Act: -0.1700

Data Index: 999053 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.0990. Min Act: -0.1700

Data Index: 735368 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.0886. Min Act: -0.1700

Data Index: 484023 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.0934. Min Act: -0.1700

Data Index: 376640 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 3.3370. Min Range: -3.3370

Max Act: 3.0923. Min Act: -0.1700

Data Index: 141659 (C4 (Web Text))

Max Activating Token Index: 562