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

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

Neuron 1561 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: 3.2755. Min Range: -3.2755

Max Act: 3.2657. Min Act: -0.1700

Data Index: 810629 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.2755. Min Act: -0.1700

Data Index: 1535061 (Python Code)

Max Activating Token Index: 601

Text #2

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.2216. Min Act: -0.1700

Data Index: 1232370 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.1962. Min Act: -0.1700

Data Index: 1084252 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.1946. Min Act: -0.1700

Data Index: 864419 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.1664. Min Act: -0.1700

Data Index: 522440 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.1446. Min Act: -0.1700

Data Index: 1631613 (Python Code)

Max Activating Token Index: 508

Text #7

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.1451. Min Act: -0.1700

Data Index: 249631 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.1258. Min Act: -0.1700

Data Index: 138916 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.1329. Min Act: -0.1700

Data Index: 1625605 (Python Code)

Max Activating Token Index: 631

Text #10

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.1153. Min Act: -0.1700

Data Index: 713092 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.0924. Min Act: -0.1700

Data Index: 24728 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.0976. Min Act: -0.1700

Data Index: 745571 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.0771. Min Act: -0.1700

Data Index: 1622621 (Python Code)

Max Activating Token Index: 27

Text #14

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.0784. Min Act: -0.1699

Data Index: 245407 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.0621. Min Act: -0.1700

Data Index: 1217705 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.0394. Min Act: -0.1700

Data Index: 1229052 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.0605. Min Act: -0.1700

Data Index: 1036810 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.0641. Min Act: -0.1700

Data Index: 840399 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 3.2755. Min Range: -3.2755

Max Act: 3.0513. Min Act: -0.1699

Data Index: 117979 (C4 (Web Text))

Max Activating Token Index: 239