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

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

Neuron 1116 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: 3.1866. Min Range: -3.1866

Max Act: 3.1866. Min Act: -0.1700

Data Index: 1446727 (Python Code)

Max Activating Token Index: 453

Text #1

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.0988. Min Act: -0.1700

Data Index: 1371171 (Python Code)

Max Activating Token Index: 474

Text #2

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.0525. Min Act: -0.1700

Data Index: 1599109 (Python Code)

Max Activating Token Index: 923

Text #3

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.0199. Min Act: -0.1700

Data Index: 1392577 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 3.1866. Min Range: -3.1866

Max Act: 2.9927. Min Act: -0.1700

Data Index: 1436758 (Python Code)

Max Activating Token Index: 399

Text #5

Max Range: 3.1866. Min Range: -3.1866

Max Act: 3.0026. Min Act: -0.1700

Data Index: 1654999 (Python Code)

Max Activating Token Index: 53

Text #6

Max Range: 3.1866. Min Range: -3.1866

Max Act: 2.9155. Min Act: -0.1700

Data Index: 1533250 (Python Code)

Max Activating Token Index: 894

Text #7

Max Range: 3.1866. Min Range: -3.1866

Max Act: 2.9576. Min Act: -0.1700

Data Index: 1407050 (Python Code)

Max Activating Token Index: 921

Text #8

Max Range: 3.1866. Min Range: -3.1866

Max Act: 2.9693. Min Act: -0.1700

Data Index: 1411712 (Python Code)

Max Activating Token Index: 311

Text #9

Max Range: 3.1866. Min Range: -3.1866

Max Act: 2.9446. Min Act: -0.1700

Data Index: 1406460 (Python Code)

Max Activating Token Index: 927

Text #10

Max Range: 3.1866. Min Range: -3.1866

Max Act: 2.9315. Min Act: -0.1700

Data Index: 1514593 (Python Code)

Max Activating Token Index: 817

Text #11

Max Range: 3.1866. Min Range: -3.1866

Max Act: 2.8994. Min Act: -0.1700

Data Index: 1528484 (Python Code)

Max Activating Token Index: 827

Text #12

Max Range: 3.1866. Min Range: -3.1866

Max Act: 2.8922. Min Act: -0.1700

Data Index: 1631156 (Python Code)

Max Activating Token Index: 271

Text #13

Max Range: 3.1866. Min Range: -3.1866

Max Act: 2.8611. Min Act: -0.1700

Data Index: 1464299 (Python Code)

Max Activating Token Index: 838

Text #14

Max Range: 3.1866. Min Range: -3.1866

Max Act: 2.8745. Min Act: -0.1700

Data Index: 1474244 (Python Code)

Max Activating Token Index: 958

Text #15

Max Range: 3.1866. Min Range: -3.1866

Max Act: 2.9022. Min Act: -0.1700

Data Index: 1427440 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 3.1866. Min Range: -3.1866

Max Act: 2.8909. Min Act: -0.1700

Data Index: 1592346 (Python Code)

Max Activating Token Index: 90

Text #17

Max Range: 3.1866. Min Range: -3.1866

Max Act: 2.8595. Min Act: -0.1700

Data Index: 1467597 (Python Code)

Max Activating Token Index: 825

Text #18

Max Range: 3.1866. Min Range: -3.1866

Max Act: 2.8626. Min Act: -0.1700

Data Index: 1443222 (Python Code)

Max Activating Token Index: 828

Text #19

Max Range: 3.1866. Min Range: -3.1866

Max Act: 2.8880. Min Act: -0.1700

Data Index: 1460775 (Python Code)

Max Activating Token Index: 397