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

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

Neuron 499 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2895. Min Range: -5.2895

Max Act: 5.2895. Min Act: -0.1700

Data Index: 244070 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 5.2895. Min Range: -5.2895

Max Act: 5.1333. Min Act: -0.1700

Data Index: 116894 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 5.2895. Min Range: -5.2895

Max Act: 5.1958. Min Act: -0.1700

Data Index: 1314972 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 5.2895. Min Range: -5.2895

Max Act: 5.1645. Min Act: -0.1700

Data Index: 1005807 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 5.2895. Min Range: -5.2895

Max Act: 5.1333. Min Act: -0.1700

Data Index: 379728 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 5.2895. Min Range: -5.2895

Max Act: 5.1958. Min Act: -0.1700

Data Index: 1004793 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 5.2895. Min Range: -5.2895

Max Act: 5.1958. Min Act: -0.1700

Data Index: 588522 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 5.2895. Min Range: -5.2895

Max Act: 5.0708. Min Act: -0.1700

Data Index: 866585 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 5.2895. Min Range: -5.2895

Max Act: 5.1020. Min Act: -0.1700

Data Index: 408362 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 5.2895. Min Range: -5.2895

Max Act: 5.1020. Min Act: -0.1700

Data Index: 240300 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 5.2895. Min Range: -5.2895

Max Act: 5.1333. Min Act: -0.1700

Data Index: 351169 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 5.2895. Min Range: -5.2895

Max Act: 5.0708. Min Act: -0.1700

Data Index: 423700 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 5.2895. Min Range: -5.2895

Max Act: 5.1645. Min Act: -0.1700

Data Index: 1147791 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 5.2895. Min Range: -5.2895

Max Act: 5.0395. Min Act: -0.1700

Data Index: 727399 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 5.2895. Min Range: -5.2895

Max Act: 5.0395. Min Act: -0.1700

Data Index: 881848 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 5.2895. Min Range: -5.2895

Max Act: 5.0083. Min Act: -0.1700

Data Index: 723538 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 5.2895. Min Range: -5.2895

Max Act: 4.9770. Min Act: -0.1700

Data Index: 140314 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 5.2895. Min Range: -5.2895

Max Act: 4.9770. Min Act: -0.1700

Data Index: 906287 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 5.2895. Min Range: -5.2895

Max Act: 4.9145. Min Act: -0.1700

Data Index: 256800 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 5.2895. Min Range: -5.2895

Max Act: 4.9458. Min Act: -0.1700

Data Index: 944147 (C4 (Web Text))

Max Activating Token Index: 375