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

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

Neuron 1410 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: 5.8595. Min Range: -5.8595

Max Act: 5.8595. Min Act: -0.1700

Data Index: 1222843 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 5.8595. Min Range: -5.8595

Max Act: 5.6095. Min Act: -0.1700

Data Index: 52738 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 5.8595. Min Range: -5.8595

Max Act: 5.6095. Min Act: -0.1700

Data Index: 272094 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 5.8595. Min Range: -5.8595

Max Act: 5.6095. Min Act: -0.1700

Data Index: 301416 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 5.8595. Min Range: -5.8595

Max Act: 5.6095. Min Act: -0.1700

Data Index: 16048 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 5.8595. Min Range: -5.8595

Max Act: 5.5470. Min Act: -0.1700

Data Index: 873587 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 5.8595. Min Range: -5.8595

Max Act: 5.3907. Min Act: -0.1700

Data Index: 502900 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 5.8595. Min Range: -5.8595

Max Act: 5.3282. Min Act: -0.1700

Data Index: 1099943 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 5.8595. Min Range: -5.8595

Max Act: 5.3282. Min Act: -0.1700

Data Index: 32980 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 5.8595. Min Range: -5.8595

Max Act: 5.2032. Min Act: -0.1700

Data Index: 76762 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 5.8595. Min Range: -5.8595

Max Act: 5.2032. Min Act: -0.1700

Data Index: 787986 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 5.8595. Min Range: -5.8595

Max Act: 5.2657. Min Act: -0.1700

Data Index: 381624 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 5.8595. Min Range: -5.8595

Max Act: 5.2657. Min Act: -0.1700

Data Index: 1162572 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 5.8595. Min Range: -5.8595

Max Act: 5.2345. Min Act: -0.1700

Data Index: 858525 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 5.8595. Min Range: -5.8595

Max Act: 5.2345. Min Act: -0.1700

Data Index: 264781 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 5.8595. Min Range: -5.8595

Max Act: 5.2345. Min Act: -0.1700

Data Index: 928253 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 5.8595. Min Range: -5.8595

Max Act: 5.2032. Min Act: -0.1700

Data Index: 972437 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 5.8595. Min Range: -5.8595

Max Act: 5.2032. Min Act: -0.1700

Data Index: 583977 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 5.8595. Min Range: -5.8595

Max Act: 5.1095. Min Act: -0.1700

Data Index: 281638 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 5.8595. Min Range: -5.8595

Max Act: 5.1720. Min Act: -0.1700

Data Index: 764256 (C4 (Web Text))

Max Activating Token Index: 465