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

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

Neuron 320 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: 4.1963. Min Range: -4.1963

Max Act: 4.1963. Min Act: -0.1698

Data Index: 910339 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1885. Min Act: -0.1700

Data Index: 1558519 (Python Code)

Max Activating Token Index: 748

Text #2

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1864. Min Act: -0.1700

Data Index: 334061 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1870. Min Act: -0.1699

Data Index: 1372679 (Python Code)

Max Activating Token Index: 249

Text #4

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1419. Min Act: -0.1695

Data Index: 1604782 (Python Code)

Max Activating Token Index: 633

Text #5

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1183. Min Act: -0.1700

Data Index: 1649386 (Python Code)

Max Activating Token Index: 522

Text #6

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.0972. Min Act: -0.1700

Data Index: 1585956 (Python Code)

Max Activating Token Index: 892

Text #7

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.0620. Min Act: -0.1700

Data Index: 1492973 (Python Code)

Max Activating Token Index: 419

Text #8

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.0598. Min Act: -0.1695

Data Index: 770143 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.0567. Min Act: -0.1691

Data Index: 1588866 (Python Code)

Max Activating Token Index: 275

Text #10

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.0107. Min Act: -0.1700

Data Index: 1494505 (Python Code)

Max Activating Token Index: 926

Text #11

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.0155. Min Act: -0.1622

Data Index: 1548232 (Python Code)

Max Activating Token Index: 734

Text #12

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.0183. Min Act: -0.1699

Data Index: 1366414 (Python Code)

Max Activating Token Index: 742

Text #13

Max Range: 4.1963. Min Range: -4.1963

Max Act: 3.9393. Min Act: -0.1700

Data Index: 378345 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 4.1963. Min Range: -4.1963

Max Act: 3.9127. Min Act: -0.1700

Data Index: 1398378 (Python Code)

Max Activating Token Index: 767

Text #15

Max Range: 4.1963. Min Range: -4.1963

Max Act: 3.9190. Min Act: -0.1697

Data Index: 1493581 (Python Code)

Max Activating Token Index: 633

Text #16

Max Range: 4.1963. Min Range: -4.1963

Max Act: 3.9183. Min Act: -0.1700

Data Index: 1403265 (Python Code)

Max Activating Token Index: 1003

Text #17

Max Range: 4.1963. Min Range: -4.1963

Max Act: 3.9133. Min Act: -0.1699

Data Index: 1400896 (Python Code)

Max Activating Token Index: 562

Text #18

Max Range: 4.1963. Min Range: -4.1963

Max Act: 3.9223. Min Act: -0.1700

Data Index: 1527138 (Python Code)

Max Activating Token Index: 311

Text #19

Max Range: 4.1963. Min Range: -4.1963

Max Act: 3.9131. Min Act: -0.1700

Data Index: 1606250 (Python Code)

Max Activating Token Index: 350