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

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

Neuron 1492 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: 3.8032. Min Range: -3.8032

Max Act: 3.8032. Min Act: -0.1700

Data Index: 507777 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.7875. Min Act: -0.1700

Data Index: 461738 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.7875. Min Act: -0.1700

Data Index: 1322802 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.7875. Min Act: -0.1700

Data Index: 272734 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.7719. Min Act: -0.1700

Data Index: 831681 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.7562. Min Act: -0.1700

Data Index: 161559 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.7719. Min Act: -0.1700

Data Index: 428966 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.7562. Min Act: -0.1700

Data Index: 168245 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.7406. Min Act: -0.1700

Data Index: 928682 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.7562. Min Act: -0.1700

Data Index: 964279 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.7562. Min Act: -0.1700

Data Index: 1093921 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.7562. Min Act: -0.1700

Data Index: 610040 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.7562. Min Act: -0.1700

Data Index: 861281 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.7562. Min Act: -0.1700

Data Index: 269403 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.7406. Min Act: -0.1700

Data Index: 381786 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.7406. Min Act: -0.1700

Data Index: 582329 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.7406. Min Act: -0.1700

Data Index: 526154 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.7249. Min Act: -0.1700

Data Index: 779910 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.7406. Min Act: -0.1700

Data Index: 880729 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.7406. Min Act: -0.1700

Data Index: 934764 (C4 (Web Text))

Max Activating Token Index: 493