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

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

Neuron 915 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: 3.4381. Min Range: -3.4381

Max Act: 3.4381. Min Act: -0.1699

Data Index: 1578798 (Python Code)

Max Activating Token Index: 394

Text #1

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.4295. Min Act: -0.1699

Data Index: 839527 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.4048. Min Act: -0.1700

Data Index: 1545197 (Python Code)

Max Activating Token Index: 656

Text #3

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3787. Min Act: -0.1700

Data Index: 1075779 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3735. Min Act: -0.1699

Data Index: 1390477 (Python Code)

Max Activating Token Index: 561

Text #5

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3107. Min Act: -0.1700

Data Index: 1108136 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.3172. Min Act: -0.1699

Data Index: 787072 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2912. Min Act: -0.1700

Data Index: 949171 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2843. Min Act: -0.1700

Data Index: 1634149 (Python Code)

Max Activating Token Index: 431

Text #9

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2726. Min Act: -0.1695

Data Index: 819994 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2741. Min Act: -0.1700

Data Index: 1479553 (Python Code)

Max Activating Token Index: 79

Text #11

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2706. Min Act: -0.1700

Data Index: 1549542 (Python Code)

Max Activating Token Index: 945

Text #12

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2817. Min Act: -0.1700

Data Index: 1459978 (Python Code)

Max Activating Token Index: 960

Text #13

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2726. Min Act: -0.1700

Data Index: 1421969 (Python Code)

Max Activating Token Index: 490

Text #14

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2600. Min Act: -0.1700

Data Index: 253419 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2526. Min Act: -0.1700

Data Index: 449656 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2640. Min Act: -0.1700

Data Index: 835872 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2461. Min Act: -0.1700

Data Index: 1576198 (Python Code)

Max Activating Token Index: 311

Text #18

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2542. Min Act: -0.1699

Data Index: 638051 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 3.4381. Min Range: -3.4381

Max Act: 3.2413. Min Act: -0.1700

Data Index: 654316 (C4 (Web Text))

Max Activating Token Index: 999