Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1229 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.9225. Min Act: -0.1700

Data Index: 1577347 (Python Code)

Max Activating Token Index: 119

Text #1

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.8599. Min Act: -0.1700

Data Index: 1591999 (Python Code)

Max Activating Token Index: 496

Text #2

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.8912. Min Act: -0.1700

Data Index: 1527636 (Python Code)

Max Activating Token Index: 1009

Text #3

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.8287. Min Act: -0.1700

Data Index: 383481 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.8756. Min Act: -0.1700

Data Index: 1538178 (Python Code)

Max Activating Token Index: 679

Text #5

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.9069. Min Act: -0.1700

Data Index: 1595601 (Python Code)

Max Activating Token Index: 928

Text #6

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.7661. Min Act: -0.1700

Data Index: 63111 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.7817. Min Act: -0.1700

Data Index: 1585103 (Python Code)

Max Activating Token Index: 221

Text #8

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.7817. Min Act: -0.1700

Data Index: 1413751 (Python Code)

Max Activating Token Index: 139

Text #9

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.6879. Min Act: -0.1699

Data Index: 1443172 (Python Code)

Max Activating Token Index: 496

Text #10

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.7505. Min Act: -0.1700

Data Index: 1502003 (Python Code)

Max Activating Token Index: 454

Text #11

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.7661. Min Act: -0.1700

Data Index: 1108332 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.6409. Min Act: -0.1700

Data Index: 1558248 (Python Code)

Max Activating Token Index: 961

Text #13

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.7348. Min Act: -0.1700

Data Index: 1198637 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.6879. Min Act: -0.1700

Data Index: 1438136 (Python Code)

Max Activating Token Index: 778

Text #15

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.6879. Min Act: -0.1700

Data Index: 1074463 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.6566. Min Act: -0.1700

Data Index: 6383 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.7505. Min Act: -0.1700

Data Index: 503868 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.6409. Min Act: -0.1700

Data Index: 1484165 (Python Code)

Max Activating Token Index: 26

Text #19

Max Range: 3.9225. Min Range: -3.9225

Max Act: 3.6566. Min Act: -0.1700

Data Index: 577872 (C4 (Web Text))

Max Activating Token Index: 468