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

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

Neuron 1462 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: 3.8186. Min Range: -3.8186

Max Act: 3.8186. Min Act: -0.1700

Data Index: 1336201 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 3.8186. Min Range: -3.8186

Max Act: 3.8186. Min Act: -0.1700

Data Index: 679065 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 3.8186. Min Range: -3.8186

Max Act: 3.6934. Min Act: -0.1700

Data Index: 1142616 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 3.8186. Min Range: -3.8186

Max Act: 3.6621. Min Act: -0.1700

Data Index: 290182 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 3.8186. Min Range: -3.8186

Max Act: 3.6621. Min Act: -0.1700

Data Index: 118936 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 3.8186. Min Range: -3.8186

Max Act: 3.6621. Min Act: -0.1700

Data Index: 163220 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 3.8186. Min Range: -3.8186

Max Act: 3.6308. Min Act: -0.1700

Data Index: 547493 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 3.8186. Min Range: -3.8186

Max Act: 3.6308. Min Act: -0.1700

Data Index: 1014422 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 3.8186. Min Range: -3.8186

Max Act: 3.6621. Min Act: -0.1700

Data Index: 16261 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 3.8186. Min Range: -3.8186

Max Act: 3.6308. Min Act: -0.1700

Data Index: 714044 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 3.8186. Min Range: -3.8186

Max Act: 3.5995. Min Act: -0.1700

Data Index: 109680 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 3.8186. Min Range: -3.8186

Max Act: 3.6152. Min Act: -0.1700

Data Index: 85309 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 3.8186. Min Range: -3.8186

Max Act: 3.5682. Min Act: -0.1700

Data Index: 590126 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 3.8186. Min Range: -3.8186

Max Act: 3.5995. Min Act: -0.1700

Data Index: 547830 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 3.8186. Min Range: -3.8186

Max Act: 3.5525. Min Act: -0.1700

Data Index: 23173 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 3.8186. Min Range: -3.8186

Max Act: 3.5682. Min Act: -0.1700

Data Index: 625417 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 3.8186. Min Range: -3.8186

Max Act: 3.5682. Min Act: -0.1700

Data Index: 254777 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 3.8186. Min Range: -3.8186

Max Act: 3.5212. Min Act: -0.1700

Data Index: 17221 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 3.8186. Min Range: -3.8186

Max Act: 3.5682. Min Act: -0.1700

Data Index: 471343 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 3.8186. Min Range: -3.8186

Max Act: 3.5212. Min Act: -0.1700

Data Index: 1091644 (C4 (Web Text))

Max Activating Token Index: 700