Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 825 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.1162. Min Range: -3.1162

Max Act: 3.1162. Min Act: -0.1700

Data Index: 1540415 (Python Code)

Max Activating Token Index: 104

Text #1

Max Range: 3.1162. Min Range: -3.1162

Max Act: 3.0937. Min Act: -0.1700

Data Index: 1369161 (Python Code)

Max Activating Token Index: 31

Text #2

Max Range: 3.1162. Min Range: -3.1162

Max Act: 3.0772. Min Act: -0.1700

Data Index: 1542320 (Python Code)

Max Activating Token Index: 222

Text #3

Max Range: 3.1162. Min Range: -3.1162

Max Act: 3.0616. Min Act: -0.1700

Data Index: 1455930 (Python Code)

Max Activating Token Index: 169

Text #4

Max Range: 3.1162. Min Range: -3.1162

Max Act: 3.0155. Min Act: -0.1700

Data Index: 1212155 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 3.1162. Min Range: -3.1162

Max Act: 3.0161. Min Act: -0.1700

Data Index: 1469997 (Python Code)

Max Activating Token Index: 37

Text #6

Max Range: 3.1162. Min Range: -3.1162

Max Act: 3.0051. Min Act: -0.1700

Data Index: 1401691 (Python Code)

Max Activating Token Index: 345

Text #7

Max Range: 3.1162. Min Range: -3.1162

Max Act: 2.9730. Min Act: -0.1700

Data Index: 1448561 (Python Code)

Max Activating Token Index: 828

Text #8

Max Range: 3.1162. Min Range: -3.1162

Max Act: 2.9525. Min Act: -0.1700

Data Index: 1475526 (Python Code)

Max Activating Token Index: 859

Text #9

Max Range: 3.1162. Min Range: -3.1162

Max Act: 2.9616. Min Act: -0.1700

Data Index: 1584087 (Python Code)

Max Activating Token Index: 1014

Text #10

Max Range: 3.1162. Min Range: -3.1162

Max Act: 2.9557. Min Act: -0.1700

Data Index: 1361912 (Python Code)

Max Activating Token Index: 382

Text #11

Max Range: 3.1162. Min Range: -3.1162

Max Act: 2.9598. Min Act: -0.1700

Data Index: 1444163 (Python Code)

Max Activating Token Index: 247

Text #12

Max Range: 3.1162. Min Range: -3.1162

Max Act: 2.9492. Min Act: -0.1700

Data Index: 1611867 (Python Code)

Max Activating Token Index: 238

Text #13

Max Range: 3.1162. Min Range: -3.1162

Max Act: 2.9384. Min Act: -0.1700

Data Index: 1489115 (Python Code)

Max Activating Token Index: 507

Text #14

Max Range: 3.1162. Min Range: -3.1162

Max Act: 2.9500. Min Act: -0.1700

Data Index: 1360702 (Python Code)

Max Activating Token Index: 828

Text #15

Max Range: 3.1162. Min Range: -3.1162

Max Act: 2.9404. Min Act: -0.1700

Data Index: 1429842 (Python Code)

Max Activating Token Index: 534

Text #16

Max Range: 3.1162. Min Range: -3.1162

Max Act: 2.9327. Min Act: -0.1700

Data Index: 1573121 (Python Code)

Max Activating Token Index: 233

Text #17

Max Range: 3.1162. Min Range: -3.1162

Max Act: 2.9114. Min Act: -0.1700

Data Index: 1596167 (Python Code)

Max Activating Token Index: 666

Text #18

Max Range: 3.1162. Min Range: -3.1162

Max Act: 2.9010. Min Act: -0.1700

Data Index: 1580669 (Python Code)

Max Activating Token Index: 67

Text #19

Max Range: 3.1162. Min Range: -3.1162

Max Act: 2.9112. Min Act: -0.1700

Data Index: 1397671 (Python Code)

Max Activating Token Index: 614