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

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

Neuron 1765 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: 4.0037. Min Range: -4.0037

Max Act: 4.0037. Min Act: -0.1700

Data Index: 819072 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 4.0037. Min Range: -4.0037

Max Act: 3.9412. Min Act: -0.1700

Data Index: 719762 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 4.0037. Min Range: -4.0037

Max Act: 3.9412. Min Act: -0.1700

Data Index: 1310282 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 4.0037. Min Range: -4.0037

Max Act: 3.9099. Min Act: -0.1700

Data Index: 211548 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 4.0037. Min Range: -4.0037

Max Act: 3.8787. Min Act: -0.1700

Data Index: 847491 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 4.0037. Min Range: -4.0037

Max Act: 3.8787. Min Act: -0.1700

Data Index: 868198 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 4.0037. Min Range: -4.0037

Max Act: 3.8787. Min Act: -0.1700

Data Index: 856712 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 4.0037. Min Range: -4.0037

Max Act: 3.8474. Min Act: -0.1700

Data Index: 380194 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 4.0037. Min Range: -4.0037

Max Act: 3.8787. Min Act: -0.1700

Data Index: 821797 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 4.0037. Min Range: -4.0037

Max Act: 3.8161. Min Act: -0.1700

Data Index: 621333 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 4.0037. Min Range: -4.0037

Max Act: 3.8474. Min Act: -0.1700

Data Index: 1327182 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 4.0037. Min Range: -4.0037

Max Act: 3.8161. Min Act: -0.1700

Data Index: 106505 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 4.0037. Min Range: -4.0037

Max Act: 3.8474. Min Act: -0.1700

Data Index: 1257285 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 4.0037. Min Range: -4.0037

Max Act: 3.8787. Min Act: -0.1700

Data Index: 1215753 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 4.0037. Min Range: -4.0037

Max Act: 3.8787. Min Act: -0.1700

Data Index: 330359 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 4.0037. Min Range: -4.0037

Max Act: 3.8161. Min Act: -0.1700

Data Index: 391425 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 4.0037. Min Range: -4.0037

Max Act: 3.8161. Min Act: -0.1700

Data Index: 11365 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 4.0037. Min Range: -4.0037

Max Act: 3.8161. Min Act: -0.1700

Data Index: 16600 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 4.0037. Min Range: -4.0037

Max Act: 3.7848. Min Act: -0.1700

Data Index: 696935 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 4.0037. Min Range: -4.0037

Max Act: 3.8161. Min Act: -0.1700

Data Index: 32555 (C4 (Web Text))

Max Activating Token Index: 471