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

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

Neuron 2022 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.4293. Min Act: -0.1700

Data Index: 87259 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.3665. Min Act: -0.1700

Data Index: 58765 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.2880. Min Act: -0.1700

Data Index: 823502 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.2723. Min Act: -0.1700

Data Index: 736674 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.2566. Min Act: -0.1700

Data Index: 718006 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.2409. Min Act: -0.1700

Data Index: 708468 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.2409. Min Act: -0.1700

Data Index: 31509 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.2409. Min Act: -0.1700

Data Index: 914229 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.2409. Min Act: -0.1700

Data Index: 463677 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.2252. Min Act: -0.1700

Data Index: 779774 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.2252. Min Act: -0.1700

Data Index: 439173 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.2094. Min Act: -0.1700

Data Index: 723750 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.1937. Min Act: -0.1700

Data Index: 676928 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.2094. Min Act: -0.1700

Data Index: 802993 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.1780. Min Act: -0.1700

Data Index: 69977 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.1937. Min Act: -0.1700

Data Index: 324372 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.1780. Min Act: -0.1700

Data Index: 238994 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.1780. Min Act: -0.1700

Data Index: 943025 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.1780. Min Act: -0.1700

Data Index: 940421 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 3.4293. Min Range: -3.4293

Max Act: 3.1622. Min Act: -0.1700

Data Index: 51672 (C4 (Web Text))

Max Activating Token Index: 469