Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1837 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.4540. Min Act: -0.1700

Data Index: 599165 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.5010. Min Act: -0.1700

Data Index: 571382 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.4383. Min Act: -0.1700

Data Index: 973618 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.4540. Min Act: -0.1700

Data Index: 469347 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.4226. Min Act: -0.1700

Data Index: 947107 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.3442. Min Act: -0.1700

Data Index: 123573 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.3442. Min Act: -0.1700

Data Index: 1174858 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.3598. Min Act: -0.1700

Data Index: 1032065 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.3598. Min Act: -0.1700

Data Index: 628751 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.3598. Min Act: -0.1700

Data Index: 1059168 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.2970. Min Act: -0.1700

Data Index: 1268967 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.3128. Min Act: -0.1700

Data Index: 1231581 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.2970. Min Act: -0.1700

Data Index: 629677 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.3128. Min Act: -0.1700

Data Index: 1080038 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.2656. Min Act: -0.1700

Data Index: 365413 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.2656. Min Act: -0.1700

Data Index: 92924 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.2342. Min Act: -0.1700

Data Index: 616862 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.2970. Min Act: -0.1700

Data Index: 520703 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.2656. Min Act: -0.1700

Data Index: 125366 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.1870. Min Act: -0.1700

Data Index: 179241 (C4 (Web Text))

Max Activating Token Index: 269