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

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

Neuron 1395 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: 5.7235. Min Range: -5.7235

Max Act: 5.7235. Min Act: -0.1700

Data Index: 1028750 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 5.7235. Min Range: -5.7235

Max Act: 5.5673. Min Act: -0.1700

Data Index: 671277 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 5.7235. Min Range: -5.7235

Max Act: 5.5048. Min Act: -0.1700

Data Index: 508600 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 5.7235. Min Range: -5.7235

Max Act: 5.5360. Min Act: -0.1700

Data Index: 792584 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 5.7235. Min Range: -5.7235

Max Act: 5.5360. Min Act: -0.1700

Data Index: 773353 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 5.7235. Min Range: -5.7235

Max Act: 5.4735. Min Act: -0.1700

Data Index: 661053 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 5.7235. Min Range: -5.7235

Max Act: 5.4735. Min Act: -0.1700

Data Index: 350010 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 5.7235. Min Range: -5.7235

Max Act: 5.3485. Min Act: -0.1700

Data Index: 1064283 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 5.7235. Min Range: -5.7235

Max Act: 5.3798. Min Act: -0.1700

Data Index: 978032 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 5.7235. Min Range: -5.7235

Max Act: 5.3173. Min Act: -0.1700

Data Index: 1338479 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 5.7235. Min Range: -5.7235

Max Act: 5.2860. Min Act: -0.1700

Data Index: 68241 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 5.7235. Min Range: -5.7235

Max Act: 5.3173. Min Act: -0.1699

Data Index: 382192 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 5.7235. Min Range: -5.7235

Max Act: 5.2235. Min Act: -0.1700

Data Index: 1113836 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 5.7235. Min Range: -5.7235

Max Act: 5.1610. Min Act: -0.1700

Data Index: 272778 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 5.7235. Min Range: -5.7235

Max Act: 5.1610. Min Act: -0.1700

Data Index: 681928 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 5.7235. Min Range: -5.7235

Max Act: 5.1610. Min Act: -0.1700

Data Index: 922164 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 5.7235. Min Range: -5.7235

Max Act: 5.0985. Min Act: -0.1700

Data Index: 1230092 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 5.7235. Min Range: -5.7235

Max Act: 5.0673. Min Act: -0.1700

Data Index: 825368 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 5.7235. Min Range: -5.7235

Max Act: 5.0360. Min Act: -0.1700

Data Index: 1292436 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 5.7235. Min Range: -5.7235

Max Act: 5.0360. Min Act: -0.1700

Data Index: 1224659 (C4 (Web Text))

Max Activating Token Index: 412