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

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

Neuron 64 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: 3.5516. Min Range: -3.5516

Max Act: 3.5508. Min Act: -0.1700

Data Index: 1488549 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.5516. Min Range: -3.5516

Max Act: 3.5516. Min Act: -0.1698

Data Index: 1454474 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.5516. Min Range: -3.5516

Max Act: 3.5009. Min Act: -0.1592

Data Index: 1490745 (Python Code)

Max Activating Token Index: 818

Text #3

Max Range: 3.5516. Min Range: -3.5516

Max Act: 3.3429. Min Act: -0.1700

Data Index: 1295510 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 3.5516. Min Range: -3.5516

Max Act: 3.3379. Min Act: -0.1691

Data Index: 1522247 (Python Code)

Max Activating Token Index: 76

Text #5

Max Range: 3.5516. Min Range: -3.5516

Max Act: 3.3281. Min Act: -0.1604

Data Index: 1577889 (Python Code)

Max Activating Token Index: 283

Text #6

Max Range: 3.5516. Min Range: -3.5516

Max Act: 3.3071. Min Act: -0.1699

Data Index: 1644393 (Python Code)

Max Activating Token Index: 303

Text #7

Max Range: 3.5516. Min Range: -3.5516

Max Act: 3.2981. Min Act: -0.1700

Data Index: 1400098 (Python Code)

Max Activating Token Index: 510

Text #8

Max Range: 3.5516. Min Range: -3.5516

Max Act: 3.2995. Min Act: -0.1700

Data Index: 1496187 (Python Code)

Max Activating Token Index: 906

Text #9

Max Range: 3.5516. Min Range: -3.5516

Max Act: 3.2976. Min Act: -0.1699

Data Index: 1433874 (Python Code)

Max Activating Token Index: 408

Text #10

Max Range: 3.5516. Min Range: -3.5516

Max Act: 3.2888. Min Act: -0.1700

Data Index: 1644520 (Python Code)

Max Activating Token Index: 294

Text #11

Max Range: 3.5516. Min Range: -3.5516

Max Act: 3.2857. Min Act: -0.1700

Data Index: 1389504 (Python Code)

Max Activating Token Index: 650

Text #12

Max Range: 3.5516. Min Range: -3.5516

Max Act: 3.2841. Min Act: -0.1699

Data Index: 1394010 (Python Code)

Max Activating Token Index: 386

Text #13

Max Range: 3.5516. Min Range: -3.5516

Max Act: 3.2749. Min Act: -0.1699

Data Index: 1448283 (Python Code)

Max Activating Token Index: 644

Text #14

Max Range: 3.5516. Min Range: -3.5516

Max Act: 3.2687. Min Act: -0.1700

Data Index: 1565672 (Python Code)

Max Activating Token Index: 1018

Text #15

Max Range: 3.5516. Min Range: -3.5516

Max Act: 3.2712. Min Act: -0.1700

Data Index: 1446829 (Python Code)

Max Activating Token Index: 698

Text #16

Max Range: 3.5516. Min Range: -3.5516

Max Act: 3.2508. Min Act: -0.1700

Data Index: 1647515 (Python Code)

Max Activating Token Index: 739

Text #17

Max Range: 3.5516. Min Range: -3.5516

Max Act: 3.2530. Min Act: -0.1700

Data Index: 1419590 (Python Code)

Max Activating Token Index: 774

Text #18

Max Range: 3.5516. Min Range: -3.5516

Max Act: 3.2661. Min Act: -0.1695

Data Index: 1408778 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 3.5516. Min Range: -3.5516

Max Act: 3.2600. Min Act: -0.1676

Data Index: 1501864 (Python Code)

Max Activating Token Index: 200