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

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

Neuron 1395 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.4012. Min Act: -0.1700

Data Index: 1299885 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.3855. Min Act: -0.1700

Data Index: 1163935 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.4012. Min Act: -0.1700

Data Index: 836030 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.3228. Min Act: -0.1700

Data Index: 948615 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.3071. Min Act: -0.1700

Data Index: 1027031 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.2914. Min Act: -0.1700

Data Index: 359963 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.2914. Min Act: -0.1700

Data Index: 177616 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.2599. Min Act: -0.1700

Data Index: 1238508 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.2285. Min Act: -0.1700

Data Index: 1280072 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.1970. Min Act: -0.1700

Data Index: 130453 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.1970. Min Act: -0.1700

Data Index: 536567 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.2285. Min Act: -0.1700

Data Index: 660977 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.1813. Min Act: -0.1700

Data Index: 966366 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.1813. Min Act: -0.1700

Data Index: 603119 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.1813. Min Act: -0.1700

Data Index: 304396 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.1498. Min Act: -0.1700

Data Index: 704775 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.1341. Min Act: -0.1700

Data Index: 117788 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.1183. Min Act: -0.1700

Data Index: 1222869 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.1498. Min Act: -0.1700

Data Index: 687362 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 3.4012. Min Range: -3.4012

Max Act: 3.1341. Min Act: -0.1700

Data Index: 1008030 (C4 (Web Text))

Max Activating Token Index: 547