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

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

Neuron 1496 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: 4.6474. Min Range: -4.6474

Max Act: 4.6474. Min Act: -0.1700

Data Index: 1648280 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.6040. Min Act: -0.1700

Data Index: 1549842 (Python Code)

Max Activating Token Index: 7

Text #2

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.5343. Min Act: -0.1700

Data Index: 1508579 (Python Code)

Max Activating Token Index: 458

Text #3

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.4803. Min Act: -0.1700

Data Index: 1567471 (Python Code)

Max Activating Token Index: 77

Text #4

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.4721. Min Act: -0.1700

Data Index: 1603517 (Python Code)

Max Activating Token Index: 983

Text #5

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.4491. Min Act: -0.1700

Data Index: 1528169 (Python Code)

Max Activating Token Index: 374

Text #6

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.4822. Min Act: -0.1700

Data Index: 1493892 (Python Code)

Max Activating Token Index: 77

Text #7

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.4331. Min Act: -0.1700

Data Index: 1638538 (Python Code)

Max Activating Token Index: 359

Text #8

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.4200. Min Act: -0.1700

Data Index: 1565122 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.4020. Min Act: -0.1700

Data Index: 1641771 (Python Code)

Max Activating Token Index: 396

Text #10

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.3773. Min Act: -0.1700

Data Index: 1501940 (Python Code)

Max Activating Token Index: 506

Text #11

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.3680. Min Act: -0.1700

Data Index: 1567448 (Python Code)

Max Activating Token Index: 5

Text #12

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.3622. Min Act: -0.1700

Data Index: 1465286 (Python Code)

Max Activating Token Index: 294

Text #13

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.3859. Min Act: -0.1700

Data Index: 1405855 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.3769. Min Act: -0.1700

Data Index: 1584778 (Python Code)

Max Activating Token Index: 223

Text #15

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.3918. Min Act: -0.1700

Data Index: 1590841 (Python Code)

Max Activating Token Index: 286

Text #16

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.3892. Min Act: -0.1700

Data Index: 1556985 (Python Code)

Max Activating Token Index: 7

Text #17

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.3281. Min Act: -0.1700

Data Index: 1365780 (Python Code)

Max Activating Token Index: 867

Text #18

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.3311. Min Act: -0.1700

Data Index: 1377226 (Python Code)

Max Activating Token Index: 115

Text #19

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.3659. Min Act: -0.1700

Data Index: 1477770 (Python Code)

Max Activating Token Index: 834