Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1338 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.1973. Min Range: -5.1973

Max Act: 5.1973. Min Act: -0.1700

Data Index: 248939 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 5.1973. Min Range: -5.1973

Max Act: 5.1661. Min Act: -0.1700

Data Index: 925327 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 5.1973. Min Range: -5.1973

Max Act: 5.1035. Min Act: -0.1700

Data Index: 1433384 (Python Code)

Max Activating Token Index: 855

Text #3

Max Range: 5.1973. Min Range: -5.1973

Max Act: 5.0410. Min Act: -0.1700

Data Index: 941042 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 5.1973. Min Range: -5.1973

Max Act: 4.9785. Min Act: -0.1700

Data Index: 1369198 (Python Code)

Max Activating Token Index: 1011

Text #5

Max Range: 5.1973. Min Range: -5.1973

Max Act: 4.9473. Min Act: -0.1700

Data Index: 49093 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 5.1973. Min Range: -5.1973

Max Act: 4.8848. Min Act: -0.1700

Data Index: 941060 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 5.1973. Min Range: -5.1973

Max Act: 4.7910. Min Act: -0.1700

Data Index: 277125 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 5.1973. Min Range: -5.1973

Max Act: 4.8535. Min Act: -0.1700

Data Index: 159984 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 5.1973. Min Range: -5.1973

Max Act: 4.8535. Min Act: -0.1700

Data Index: 1012426 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 5.1973. Min Range: -5.1973

Max Act: 4.8535. Min Act: -0.1700

Data Index: 1009768 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 5.1973. Min Range: -5.1973

Max Act: 4.8535. Min Act: -0.1700

Data Index: 1345431 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 5.1973. Min Range: -5.1973

Max Act: 4.8223. Min Act: -0.1700

Data Index: 1026183 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 5.1973. Min Range: -5.1973

Max Act: 4.7910. Min Act: -0.1700

Data Index: 635314 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 5.1973. Min Range: -5.1973

Max Act: 4.7598. Min Act: -0.1700

Data Index: 100540 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 5.1973. Min Range: -5.1973

Max Act: 4.7598. Min Act: -0.1700

Data Index: 258549 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 5.1973. Min Range: -5.1973

Max Act: 4.7598. Min Act: -0.1700

Data Index: 1035678 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 5.1973. Min Range: -5.1973

Max Act: 4.7598. Min Act: -0.1700

Data Index: 333013 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 5.1973. Min Range: -5.1973

Max Act: 4.7598. Min Act: -0.1700

Data Index: 1356591 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 5.1973. Min Range: -5.1973

Max Act: 4.7598. Min Act: -0.1700

Data Index: 1166520 (C4 (Web Text))

Max Activating Token Index: 1019