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

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

Neuron 954 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: 3.3215. Min Range: -3.3215

Max Act: 3.3215. Min Act: -0.1692

Data Index: 1022212 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.3094. Min Act: -0.1682

Data Index: 1578952 (Python Code)

Max Activating Token Index: 311

Text #2

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.2113. Min Act: -0.1700

Data Index: 678644 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.2205. Min Act: -0.1682

Data Index: 1544656 (Python Code)

Max Activating Token Index: 624

Text #4

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.1752. Min Act: -0.1682

Data Index: 1579379 (Python Code)

Max Activating Token Index: 180

Text #5

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.1733. Min Act: -0.1682

Data Index: 1428636 (Python Code)

Max Activating Token Index: 548

Text #6

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.1497. Min Act: -0.1682

Data Index: 302188 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.1436. Min Act: -0.1700

Data Index: 1296147 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.1102. Min Act: -0.1695

Data Index: 797111 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.1207. Min Act: -0.1700

Data Index: 1486447 (Python Code)

Max Activating Token Index: 381

Text #10

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.1212. Min Act: -0.1682

Data Index: 1532960 (Python Code)

Max Activating Token Index: 294

Text #11

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.1382. Min Act: -0.1700

Data Index: 290366 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.0891. Min Act: -0.1700

Data Index: 1558137 (Python Code)

Max Activating Token Index: 695

Text #13

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.0893. Min Act: -0.1699

Data Index: 1439689 (Python Code)

Max Activating Token Index: 76

Text #14

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.0788. Min Act: -0.1691

Data Index: 1599357 (Python Code)

Max Activating Token Index: 734

Text #15

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.0987. Min Act: -0.1700

Data Index: 37364 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.0885. Min Act: -0.1700

Data Index: 896771 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.0834. Min Act: -0.1694

Data Index: 1547798 (Python Code)

Max Activating Token Index: 727

Text #18

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.0906. Min Act: -0.1699

Data Index: 1479744 (Python Code)

Max Activating Token Index: 949

Text #19

Max Range: 3.3215. Min Range: -3.3215

Max Act: 3.0756. Min Act: -0.1691

Data Index: 1586181 (Python Code)

Max Activating Token Index: 17