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

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

Neuron 1975 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: 5.2559. Min Range: -5.2559

Max Act: 5.2559. Min Act: -0.1700

Data Index: 729205 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.2247. Min Act: -0.1700

Data Index: 67340 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.1466. Min Act: -0.1700

Data Index: 101373 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.1934. Min Act: -0.1700

Data Index: 1306889 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.1309. Min Act: -0.1700

Data Index: 311480 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.1309. Min Act: -0.1700

Data Index: 905341 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0997. Min Act: -0.1700

Data Index: 979359 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.1466. Min Act: -0.1700

Data Index: 1038197 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0684. Min Act: -0.1700

Data Index: 1233220 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.1153. Min Act: -0.1700

Data Index: 669270 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0372. Min Act: -0.1700

Data Index: 609415 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0216. Min Act: -0.1700

Data Index: 939975 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0059. Min Act: -0.1700

Data Index: 658717 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0216. Min Act: -0.1700

Data Index: 727011 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 5.2559. Min Range: -5.2559

Max Act: 4.9903. Min Act: -0.1700

Data Index: 494968 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 5.2559. Min Range: -5.2559

Max Act: 4.9903. Min Act: -0.1700

Data Index: 946368 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0528. Min Act: -0.1700

Data Index: 1159604 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0528. Min Act: -0.1700

Data Index: 197042 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0059. Min Act: -0.1700

Data Index: 290256 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 5.2559. Min Range: -5.2559

Max Act: 4.9278. Min Act: -0.1700

Data Index: 919559 (C4 (Web Text))

Max Activating Token Index: 203