Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 342 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.8060. Min Act: -0.1700

Data Index: 864866 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.8060. Min Act: -0.1700

Data Index: 714029 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.7747. Min Act: -0.1700

Data Index: 1179695 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.7747. Min Act: -0.1700

Data Index: 1071179 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.6809. Min Act: -0.1700

Data Index: 453251 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.7434. Min Act: -0.1700

Data Index: 301148 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.7434. Min Act: -0.1700

Data Index: 1216574 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.7747. Min Act: -0.1700

Data Index: 1019905 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.7434. Min Act: -0.1700

Data Index: 993319 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.7434. Min Act: -0.1700

Data Index: 128121 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.6809. Min Act: -0.1700

Data Index: 615228 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.7121. Min Act: -0.1700

Data Index: 1053323 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.6809. Min Act: -0.1700

Data Index: 697525 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.7434. Min Act: -0.1700

Data Index: 281202 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.7121. Min Act: -0.1700

Data Index: 307735 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.7121. Min Act: -0.1700

Data Index: 992155 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.7121. Min Act: -0.1700

Data Index: 502423 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.7121. Min Act: -0.1700

Data Index: 1275698 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.7121. Min Act: -0.1700

Data Index: 623686 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 3.8060. Min Range: -3.8060

Max Act: 3.7121. Min Act: -0.1700

Data Index: 1122550 (C4 (Web Text))

Max Activating Token Index: 535