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

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

Neuron 762 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: 4.1143. Min Range: -4.1143

Max Act: 4.1143. Min Act: -0.1700

Data Index: 1431634 (Python Code)

Max Activating Token Index: 881

Text #1

Max Range: 4.1143. Min Range: -4.1143

Max Act: 4.0365. Min Act: -0.1700

Data Index: 58246 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 4.1143. Min Range: -4.1143

Max Act: 4.0069. Min Act: -0.1700

Data Index: 1111702 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 4.1143. Min Range: -4.1143

Max Act: 4.0007. Min Act: -0.1700

Data Index: 1495910 (Python Code)

Max Activating Token Index: 515

Text #4

Max Range: 4.1143. Min Range: -4.1143

Max Act: 4.0092. Min Act: -0.1700

Data Index: 1044850 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 4.1143. Min Range: -4.1143

Max Act: 3.9901. Min Act: -0.1700

Data Index: 826594 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 4.1143. Min Range: -4.1143

Max Act: 3.9365. Min Act: -0.1700

Data Index: 1606505 (Python Code)

Max Activating Token Index: 319

Text #7

Max Range: 4.1143. Min Range: -4.1143

Max Act: 3.9160. Min Act: -0.1700

Data Index: 814281 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 4.1143. Min Range: -4.1143

Max Act: 3.9058. Min Act: -0.1700

Data Index: 1594179 (Python Code)

Max Activating Token Index: 151

Text #9

Max Range: 4.1143. Min Range: -4.1143

Max Act: 3.9086. Min Act: -0.1700

Data Index: 1385454 (Python Code)

Max Activating Token Index: 702

Text #10

Max Range: 4.1143. Min Range: -4.1143

Max Act: 3.9125. Min Act: -0.1700

Data Index: 132145 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 4.1143. Min Range: -4.1143

Max Act: 3.9269. Min Act: -0.1700

Data Index: 394663 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 4.1143. Min Range: -4.1143

Max Act: 3.8960. Min Act: -0.1700

Data Index: 1532475 (Python Code)

Max Activating Token Index: 96

Text #13

Max Range: 4.1143. Min Range: -4.1143

Max Act: 3.8975. Min Act: -0.1700

Data Index: 1618517 (Python Code)

Max Activating Token Index: 303

Text #14

Max Range: 4.1143. Min Range: -4.1143

Max Act: 3.8779. Min Act: -0.1700

Data Index: 1509720 (Python Code)

Max Activating Token Index: 726

Text #15

Max Range: 4.1143. Min Range: -4.1143

Max Act: 3.9073. Min Act: -0.1700

Data Index: 1449072 (Python Code)

Max Activating Token Index: 1007

Text #16

Max Range: 4.1143. Min Range: -4.1143

Max Act: 3.9018. Min Act: -0.1694

Data Index: 824835 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 4.1143. Min Range: -4.1143

Max Act: 3.8438. Min Act: -0.1700

Data Index: 218192 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 4.1143. Min Range: -4.1143

Max Act: 3.8394. Min Act: -0.1700

Data Index: 1624681 (Python Code)

Max Activating Token Index: 459

Text #19

Max Range: 4.1143. Min Range: -4.1143

Max Act: 3.8459. Min Act: -0.1700

Data Index: 1491222 (Python Code)

Max Activating Token Index: 207