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

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

Neuron 958 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.8293. Min Act: -0.1700

Data Index: 895201 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.7668. Min Act: -0.1700

Data Index: 890626 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.7980. Min Act: -0.1700

Data Index: 911185 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.7980. Min Act: -0.1700

Data Index: 552289 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.7355. Min Act: -0.1700

Data Index: 1297355 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.7355. Min Act: -0.1700

Data Index: 889874 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.6416. Min Act: -0.1700

Data Index: 1342027 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.6729. Min Act: -0.1700

Data Index: 583466 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.6416. Min Act: -0.1700

Data Index: 332127 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.7042. Min Act: -0.1700

Data Index: 270566 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.6416. Min Act: -0.1700

Data Index: 376344 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.6103. Min Act: -0.1700

Data Index: 446621 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.6103. Min Act: -0.1700

Data Index: 598984 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.6103. Min Act: -0.1700

Data Index: 629015 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.6103. Min Act: -0.1700

Data Index: 147986 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.6103. Min Act: -0.1700

Data Index: 1070827 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.6103. Min Act: -0.1700

Data Index: 536064 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.5790. Min Act: -0.1700

Data Index: 50089 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.5790. Min Act: -0.1700

Data Index: 894373 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 3.8293. Min Range: -3.8293

Max Act: 3.6103. Min Act: -0.1700

Data Index: 560075 (C4 (Web Text))

Max Activating Token Index: 190