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

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

Neuron 912 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: 2.8427. Min Range: -2.8427

Max Act: 2.8427. Min Act: -0.1700

Data Index: 498130 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 2.8427. Min Range: -2.8427

Max Act: 2.8181. Min Act: -0.1700

Data Index: 1351316 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 2.8427. Min Range: -2.8427

Max Act: 2.7679. Min Act: -0.1700

Data Index: 328752 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 2.8427. Min Range: -2.8427

Max Act: 2.7552. Min Act: -0.1700

Data Index: 193364 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 2.8427. Min Range: -2.8427

Max Act: 2.7564. Min Act: -0.1700

Data Index: 638323 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 2.8427. Min Range: -2.8427

Max Act: 2.7479. Min Act: -0.1700

Data Index: 332599 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 2.8427. Min Range: -2.8427

Max Act: 2.7359. Min Act: -0.1700

Data Index: 269330 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 2.8427. Min Range: -2.8427

Max Act: 2.7378. Min Act: -0.1699

Data Index: 945377 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 2.8427. Min Range: -2.8427

Max Act: 2.7296. Min Act: -0.1700

Data Index: 554538 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 2.8427. Min Range: -2.8427

Max Act: 2.7236. Min Act: -0.1700

Data Index: 666979 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 2.8427. Min Range: -2.8427

Max Act: 2.7170. Min Act: -0.1700

Data Index: 1012360 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 2.8427. Min Range: -2.8427

Max Act: 2.7134. Min Act: -0.1700

Data Index: 270794 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 2.8427. Min Range: -2.8427

Max Act: 2.7210. Min Act: -0.1700

Data Index: 502045 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 2.8427. Min Range: -2.8427

Max Act: 2.6976. Min Act: -0.1700

Data Index: 1306989 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 2.8427. Min Range: -2.8427

Max Act: 2.6967. Min Act: -0.1700

Data Index: 324738 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 2.8427. Min Range: -2.8427

Max Act: 2.6752. Min Act: -0.1700

Data Index: 531616 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 2.8427. Min Range: -2.8427

Max Act: 2.6843. Min Act: -0.1700

Data Index: 1303149 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 2.8427. Min Range: -2.8427

Max Act: 2.6682. Min Act: -0.1700

Data Index: 185586 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 2.8427. Min Range: -2.8427

Max Act: 2.6906. Min Act: -0.1700

Data Index: 999989 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 2.8427. Min Range: -2.8427

Max Act: 2.6638. Min Act: -0.1700

Data Index: 144041 (C4 (Web Text))

Max Activating Token Index: 704