Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 848 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.0055. Min Range: -5.0055

Max Act: 5.0055. Min Act: -0.1700

Data Index: 1563569 (Python Code)

Max Activating Token Index: 150

Text #1

Max Range: 5.0055. Min Range: -5.0055

Max Act: 4.7555. Min Act: -0.1700

Data Index: 1528183 (Python Code)

Max Activating Token Index: 314

Text #2

Max Range: 5.0055. Min Range: -5.0055

Max Act: 4.7243. Min Act: -0.1700

Data Index: 1615689 (Python Code)

Max Activating Token Index: 51

Text #3

Max Range: 5.0055. Min Range: -5.0055

Max Act: 4.5993. Min Act: -0.1700

Data Index: 441139 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 5.0055. Min Range: -5.0055

Max Act: 4.6305. Min Act: -0.1700

Data Index: 1586764 (Python Code)

Max Activating Token Index: 536

Text #5

Max Range: 5.0055. Min Range: -5.0055

Max Act: 4.6930. Min Act: -0.1699

Data Index: 1446277 (Python Code)

Max Activating Token Index: 110

Text #6

Max Range: 5.0055. Min Range: -5.0055

Max Act: 4.6305. Min Act: -0.1700

Data Index: 1458823 (Python Code)

Max Activating Token Index: 29

Text #7

Max Range: 5.0055. Min Range: -5.0055

Max Act: 4.5680. Min Act: -0.1700

Data Index: 1522695 (Python Code)

Max Activating Token Index: 694

Text #8

Max Range: 5.0055. Min Range: -5.0055

Max Act: 4.6305. Min Act: -0.1700

Data Index: 1583256 (Python Code)

Max Activating Token Index: 481

Text #9

Max Range: 5.0055. Min Range: -5.0055

Max Act: 4.5680. Min Act: -0.1700

Data Index: 1572076 (Python Code)

Max Activating Token Index: 540

Text #10

Max Range: 5.0055. Min Range: -5.0055

Max Act: 4.5680. Min Act: -0.1700

Data Index: 1555340 (Python Code)

Max Activating Token Index: 86

Text #11

Max Range: 5.0055. Min Range: -5.0055

Max Act: 4.5055. Min Act: -0.1700

Data Index: 829232 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 5.0055. Min Range: -5.0055

Max Act: 4.5055. Min Act: -0.1700

Data Index: 1586385 (Python Code)

Max Activating Token Index: 427

Text #13

Max Range: 5.0055. Min Range: -5.0055

Max Act: 4.5055. Min Act: -0.1700

Data Index: 1479755 (Python Code)

Max Activating Token Index: 491

Text #14

Max Range: 5.0055. Min Range: -5.0055

Max Act: 4.4742. Min Act: -0.1700

Data Index: 1498172 (Python Code)

Max Activating Token Index: 669

Text #15

Max Range: 5.0055. Min Range: -5.0055

Max Act: 4.4742. Min Act: -0.1700

Data Index: 1413251 (Python Code)

Max Activating Token Index: 432

Text #16

Max Range: 5.0055. Min Range: -5.0055

Max Act: 4.4430. Min Act: -0.1700

Data Index: 1414461 (Python Code)

Max Activating Token Index: 366

Text #17

Max Range: 5.0055. Min Range: -5.0055

Max Act: 4.5055. Min Act: -0.1700

Data Index: 1642136 (Python Code)

Max Activating Token Index: 257

Text #18

Max Range: 5.0055. Min Range: -5.0055

Max Act: 4.4430. Min Act: -0.1700

Data Index: 1607258 (Python Code)

Max Activating Token Index: 709

Text #19

Max Range: 5.0055. Min Range: -5.0055

Max Act: 4.4742. Min Act: -0.1700

Data Index: 1614210 (Python Code)

Max Activating Token Index: 525