Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 415 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 8.1280. Min Range: -8.1280

Max Act: 8.1280. Min Act: -0.1700

Data Index: 100669 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.8780. Min Act: -0.1700

Data Index: 300490 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.8780. Min Act: -0.1700

Data Index: 805269 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.8780. Min Act: -0.1700

Data Index: 980133 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.8155. Min Act: -0.1700

Data Index: 1063784 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.8155. Min Act: -0.1700

Data Index: 116031 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.8155. Min Act: -0.1700

Data Index: 217798 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.7530. Min Act: -0.1700

Data Index: 1060918 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.7842. Min Act: -0.1700

Data Index: 659215 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.7842. Min Act: -0.1700

Data Index: 325782 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.7217. Min Act: -0.1700

Data Index: 552286 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.6905. Min Act: -0.1700

Data Index: 1092939 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.7217. Min Act: -0.1700

Data Index: 498613 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.6905. Min Act: -0.1700

Data Index: 452431 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.6592. Min Act: -0.1700

Data Index: 1085743 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.7530. Min Act: -0.1700

Data Index: 651775 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.5967. Min Act: -0.1700

Data Index: 1211700 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.6905. Min Act: -0.1700

Data Index: 1347601 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.6280. Min Act: -0.1700

Data Index: 765835 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 8.1280. Min Range: -8.1280

Max Act: 7.6280. Min Act: -0.1700

Data Index: 934018 (C4 (Web Text))

Max Activating Token Index: 961