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

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

Neuron 924 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.2925. Min Act: -0.1700

Data Index: 755874 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.2611. Min Act: -0.1700

Data Index: 989082 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.2296. Min Act: -0.1700

Data Index: 1205010 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.2139. Min Act: -0.1700

Data Index: 880642 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1982. Min Act: -0.1700

Data Index: 880494 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1824. Min Act: -0.1700

Data Index: 46235 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1982. Min Act: -0.1700

Data Index: 1082078 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1352. Min Act: -0.1700

Data Index: 345454 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.2139. Min Act: -0.1700

Data Index: 1117839 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1510. Min Act: -0.1700

Data Index: 655313 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1037. Min Act: -0.1700

Data Index: 702418 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1037. Min Act: -0.1700

Data Index: 1184121 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1194. Min Act: -0.1700

Data Index: 1042751 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.0721. Min Act: -0.1700

Data Index: 267517 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.0721. Min Act: -0.1700

Data Index: 229027 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.1037. Min Act: -0.1700

Data Index: 1037925 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.0721. Min Act: -0.1700

Data Index: 288272 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.0564. Min Act: -0.1700

Data Index: 752487 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.0721. Min Act: -0.1700

Data Index: 356224 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 3.2925. Min Range: -3.2925

Max Act: 3.0406. Min Act: -0.1700

Data Index: 716064 (C4 (Web Text))

Max Activating Token Index: 838