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

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

Neuron 554 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: 8.5130. Min Range: -8.5130

Max Act: 8.5130. Min Act: -0.1700

Data Index: 1111088 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 8.5130. Min Range: -8.5130

Max Act: 8.3880. Min Act: -0.1700

Data Index: 294962 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 8.5130. Min Range: -8.5130

Max Act: 8.1692. Min Act: -0.1700

Data Index: 1022555 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 8.5130. Min Range: -8.5130

Max Act: 8.1380. Min Act: -0.1700

Data Index: 284040 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 8.5130. Min Range: -8.5130

Max Act: 7.9817. Min Act: -0.1700

Data Index: 486414 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 8.5130. Min Range: -8.5130

Max Act: 8.0130. Min Act: -0.1700

Data Index: 940608 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 8.5130. Min Range: -8.5130

Max Act: 8.0130. Min Act: -0.1700

Data Index: 1176989 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 8.5130. Min Range: -8.5130

Max Act: 7.9817. Min Act: -0.1700

Data Index: 565664 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 8.5130. Min Range: -8.5130

Max Act: 8.0442. Min Act: -0.1700

Data Index: 1358253 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 8.5130. Min Range: -8.5130

Max Act: 8.0130. Min Act: -0.1700

Data Index: 1034939 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 8.5130. Min Range: -8.5130

Max Act: 8.0130. Min Act: -0.1700

Data Index: 375631 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 8.5130. Min Range: -8.5130

Max Act: 7.9192. Min Act: -0.1700

Data Index: 1206451 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 8.5130. Min Range: -8.5130

Max Act: 7.9505. Min Act: -0.1700

Data Index: 614535 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 8.5130. Min Range: -8.5130

Max Act: 7.9192. Min Act: -0.1700

Data Index: 1171716 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 8.5130. Min Range: -8.5130

Max Act: 8.0130. Min Act: -0.1700

Data Index: 590069 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 8.5130. Min Range: -8.5130

Max Act: 7.9817. Min Act: -0.1700

Data Index: 436165 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 8.5130. Min Range: -8.5130

Max Act: 7.8567. Min Act: -0.1700

Data Index: 1244879 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 8.5130. Min Range: -8.5130

Max Act: 7.9817. Min Act: -0.1700

Data Index: 177553 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 8.5130. Min Range: -8.5130

Max Act: 7.7630. Min Act: -0.1700

Data Index: 1066251 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 8.5130. Min Range: -8.5130

Max Act: 7.8567. Min Act: -0.1700

Data Index: 1022128 (C4 (Web Text))

Max Activating Token Index: 819