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

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

Neuron 1973 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: 4.9090. Min Range: -4.9090

Max Act: 4.9090. Min Act: -0.1700

Data Index: 1604582 (Python Code)

Max Activating Token Index: 849

Text #1

Max Range: 4.9090. Min Range: -4.9090

Max Act: 4.7894. Min Act: -0.1699

Data Index: 333527 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 4.9090. Min Range: -4.9090

Max Act: 4.7664. Min Act: -0.1700

Data Index: 1391426 (Python Code)

Max Activating Token Index: 683

Text #3

Max Range: 4.9090. Min Range: -4.9090

Max Act: 4.7509. Min Act: -0.1699

Data Index: 1397601 (Python Code)

Max Activating Token Index: 94

Text #4

Max Range: 4.9090. Min Range: -4.9090

Max Act: 4.7227. Min Act: -0.1700

Data Index: 1520368 (Python Code)

Max Activating Token Index: 417

Text #5

Max Range: 4.9090. Min Range: -4.9090

Max Act: 4.7078. Min Act: -0.1700

Data Index: 1340713 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 4.9090. Min Range: -4.9090

Max Act: 4.7195. Min Act: -0.1699

Data Index: 1446735 (Python Code)

Max Activating Token Index: 521

Text #7

Max Range: 4.9090. Min Range: -4.9090

Max Act: 4.7211. Min Act: -0.1696

Data Index: 884713 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 4.9090. Min Range: -4.9090

Max Act: 4.6314. Min Act: -0.1700

Data Index: 569585 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 4.9090. Min Range: -4.9090

Max Act: 4.6476. Min Act: -0.1684

Data Index: 467131 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 4.9090. Min Range: -4.9090

Max Act: 4.6528. Min Act: -0.1699

Data Index: 1536487 (Python Code)

Max Activating Token Index: 794

Text #11

Max Range: 4.9090. Min Range: -4.9090

Max Act: 4.6708. Min Act: -0.1700

Data Index: 1600117 (Python Code)

Max Activating Token Index: 729

Text #12

Max Range: 4.9090. Min Range: -4.9090

Max Act: 4.6069. Min Act: -0.1699

Data Index: 1011108 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 4.9090. Min Range: -4.9090

Max Act: 4.6169. Min Act: -0.1700

Data Index: 1592157 (Python Code)

Max Activating Token Index: 307

Text #14

Max Range: 4.9090. Min Range: -4.9090

Max Act: 4.5674. Min Act: -0.1700

Data Index: 1520541 (Python Code)

Max Activating Token Index: 51

Text #15

Max Range: 4.9090. Min Range: -4.9090

Max Act: 4.5558. Min Act: -0.1700

Data Index: 1515837 (Python Code)

Max Activating Token Index: 122

Text #16

Max Range: 4.9090. Min Range: -4.9090

Max Act: 4.5224. Min Act: -0.1699

Data Index: 375072 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 4.9090. Min Range: -4.9090

Max Act: 4.5185. Min Act: -0.1700

Data Index: 1210135 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 4.9090. Min Range: -4.9090

Max Act: 4.4796. Min Act: -0.1700

Data Index: 1370169 (Python Code)

Max Activating Token Index: 732

Text #19

Max Range: 4.9090. Min Range: -4.9090

Max Act: 4.4995. Min Act: -0.1699

Data Index: 1579277 (Python Code)

Max Activating Token Index: 227