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

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

Neuron 1604 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: 4.1448. Min Range: -4.1448

Max Act: 4.1448. Min Act: -0.1700

Data Index: 1137767 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 4.1448. Min Range: -4.1448

Max Act: 4.1109. Min Act: -0.1699

Data Index: 733638 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 4.1448. Min Range: -4.1448

Max Act: 4.1276. Min Act: -0.1700

Data Index: 349631 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 4.1448. Min Range: -4.1448

Max Act: 4.1277. Min Act: -0.1700

Data Index: 212905 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 4.1448. Min Range: -4.1448

Max Act: 4.1118. Min Act: -0.1700

Data Index: 28149 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 4.1448. Min Range: -4.1448

Max Act: 4.1246. Min Act: -0.1700

Data Index: 22699 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 4.1448. Min Range: -4.1448

Max Act: 4.0893. Min Act: -0.1700

Data Index: 1149214 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 4.1448. Min Range: -4.1448

Max Act: 4.0645. Min Act: -0.1700

Data Index: 234213 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 4.1448. Min Range: -4.1448

Max Act: 4.0906. Min Act: -0.1700

Data Index: 775557 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 4.1448. Min Range: -4.1448

Max Act: 4.0713. Min Act: -0.1700

Data Index: 1052096 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 4.1448. Min Range: -4.1448

Max Act: 4.0880. Min Act: -0.1700

Data Index: 1004022 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 4.1448. Min Range: -4.1448

Max Act: 4.0624. Min Act: -0.1700

Data Index: 1187811 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 4.1448. Min Range: -4.1448

Max Act: 4.0454. Min Act: -0.1700

Data Index: 195608 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 4.1448. Min Range: -4.1448

Max Act: 4.0481. Min Act: -0.1700

Data Index: 498919 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 4.1448. Min Range: -4.1448

Max Act: 4.0457. Min Act: -0.1700

Data Index: 181792 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 4.1448. Min Range: -4.1448

Max Act: 4.0571. Min Act: -0.1700

Data Index: 19694 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 4.1448. Min Range: -4.1448

Max Act: 4.0356. Min Act: -0.1700

Data Index: 842249 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 4.1448. Min Range: -4.1448

Max Act: 4.0438. Min Act: -0.1700

Data Index: 377274 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 4.1448. Min Range: -4.1448

Max Act: 4.0351. Min Act: -0.1699

Data Index: 529696 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 4.1448. Min Range: -4.1448

Max Act: 4.0362. Min Act: -0.1700

Data Index: 475682 (C4 (Web Text))

Max Activating Token Index: 287