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

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

Neuron 1112 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: 3.4523. Min Range: -3.4523

Max Act: 3.4523. Min Act: -0.1700

Data Index: 1465595 (Python Code)

Max Activating Token Index: 67

Text #1

Max Range: 3.4523. Min Range: -3.4523

Max Act: 3.3656. Min Act: -0.1700

Data Index: 1481319 (Python Code)

Max Activating Token Index: 522

Text #2

Max Range: 3.4523. Min Range: -3.4523

Max Act: 3.3518. Min Act: -0.1700

Data Index: 1388835 (Python Code)

Max Activating Token Index: 818

Text #3

Max Range: 3.4523. Min Range: -3.4523

Max Act: 3.3198. Min Act: -0.1700

Data Index: 1383479 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 3.4523. Min Range: -3.4523

Max Act: 3.2690. Min Act: -0.1700

Data Index: 1522350 (Python Code)

Max Activating Token Index: 750

Text #5

Max Range: 3.4523. Min Range: -3.4523

Max Act: 3.2939. Min Act: -0.1700

Data Index: 1576951 (Python Code)

Max Activating Token Index: 568

Text #6

Max Range: 3.4523. Min Range: -3.4523

Max Act: 3.2851. Min Act: -0.1694

Data Index: 1629358 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 3.4523. Min Range: -3.4523

Max Act: 3.2989. Min Act: -0.1699

Data Index: 1568430 (Python Code)

Max Activating Token Index: 354

Text #8

Max Range: 3.4523. Min Range: -3.4523

Max Act: 3.2936. Min Act: -0.1700

Data Index: 1572084 (Python Code)

Max Activating Token Index: 53

Text #9

Max Range: 3.4523. Min Range: -3.4523

Max Act: 3.2804. Min Act: -0.1699

Data Index: 1608133 (Python Code)

Max Activating Token Index: 427

Text #10

Max Range: 3.4523. Min Range: -3.4523

Max Act: 3.2782. Min Act: -0.1700

Data Index: 1492694 (Python Code)

Max Activating Token Index: 33

Text #11

Max Range: 3.4523. Min Range: -3.4523

Max Act: 3.2729. Min Act: -0.1700

Data Index: 1491388 (Python Code)

Max Activating Token Index: 736

Text #12

Max Range: 3.4523. Min Range: -3.4523

Max Act: 3.2561. Min Act: -0.1700

Data Index: 1557834 (Python Code)

Max Activating Token Index: 973

Text #13

Max Range: 3.4523. Min Range: -3.4523

Max Act: 3.2508. Min Act: -0.1700

Data Index: 1637047 (Python Code)

Max Activating Token Index: 375

Text #14

Max Range: 3.4523. Min Range: -3.4523

Max Act: 3.2489. Min Act: -0.1700

Data Index: 1546058 (Python Code)

Max Activating Token Index: 785

Text #15

Max Range: 3.4523. Min Range: -3.4523

Max Act: 3.2436. Min Act: -0.1700

Data Index: 1427111 (Python Code)

Max Activating Token Index: 856

Text #16

Max Range: 3.4523. Min Range: -3.4523

Max Act: 3.2278. Min Act: -0.1700

Data Index: 1397339 (Python Code)

Max Activating Token Index: 794

Text #17

Max Range: 3.4523. Min Range: -3.4523

Max Act: 3.2085. Min Act: -0.1700

Data Index: 1542789 (Python Code)

Max Activating Token Index: 98

Text #18

Max Range: 3.4523. Min Range: -3.4523

Max Act: 3.2207. Min Act: -0.1698

Data Index: 1483523 (Python Code)

Max Activating Token Index: 871

Text #19

Max Range: 3.4523. Min Range: -3.4523

Max Act: 3.2004. Min Act: -0.1700

Data Index: 1486948 (Python Code)

Max Activating Token Index: 133