Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 196 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.2705. Min Act: -0.1700

Data Index: 778904 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.1604. Min Act: -0.1700

Data Index: 332440 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.1289. Min Act: -0.1700

Data Index: 727512 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.1446. Min Act: -0.1700

Data Index: 400135 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.1289. Min Act: -0.1700

Data Index: 689242 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.1289. Min Act: -0.1700

Data Index: 914035 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.1289. Min Act: -0.1700

Data Index: 1101330 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.1289. Min Act: -0.1700

Data Index: 297398 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.1289. Min Act: -0.1700

Data Index: 1349775 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.1289. Min Act: -0.1700

Data Index: 1248744 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.1131. Min Act: -0.1700

Data Index: 308982 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.0973. Min Act: -0.1700

Data Index: 629015 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.1131. Min Act: -0.1700

Data Index: 378048 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.0973. Min Act: -0.1700

Data Index: 1300836 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.1131. Min Act: -0.1700

Data Index: 1401246 (Python Code)

Max Activating Token Index: 944

Text #15

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.0973. Min Act: -0.1700

Data Index: 1606840 (Python Code)

Max Activating Token Index: 839

Text #16

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.0816. Min Act: -0.1700

Data Index: 302848 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.0973. Min Act: -0.1700

Data Index: 176222 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.0816. Min Act: -0.1700

Data Index: 619591 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.0658. Min Act: -0.1700

Data Index: 707532 (C4 (Web Text))

Max Activating Token Index: 426