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

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

Neuron 1240 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: 5.1643. Min Range: -5.1643

Max Act: 5.1643. Min Act: -0.1700

Data Index: 1116849 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 5.1643. Min Range: -5.1643

Max Act: 5.1018. Min Act: -0.1700

Data Index: 212005 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 5.1643. Min Range: -5.1643

Max Act: 5.0393. Min Act: -0.1700

Data Index: 348631 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 5.1643. Min Range: -5.1643

Max Act: 5.0393. Min Act: -0.1700

Data Index: 84646 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 5.1643. Min Range: -5.1643

Max Act: 5.0080. Min Act: -0.1700

Data Index: 164780 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 5.1643. Min Range: -5.1643

Max Act: 4.9143. Min Act: -0.1700

Data Index: 375479 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 5.1643. Min Range: -5.1643

Max Act: 4.8830. Min Act: -0.1700

Data Index: 1132755 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 5.1643. Min Range: -5.1643

Max Act: 4.9143. Min Act: -0.1700

Data Index: 1321602 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 5.1643. Min Range: -5.1643

Max Act: 4.8205. Min Act: -0.1700

Data Index: 1108609 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 5.1643. Min Range: -5.1643

Max Act: 4.8518. Min Act: -0.1700

Data Index: 1151558 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 5.1643. Min Range: -5.1643

Max Act: 4.8205. Min Act: -0.1700

Data Index: 1096373 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 5.1643. Min Range: -5.1643

Max Act: 4.8205. Min Act: -0.1700

Data Index: 301638 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 5.1643. Min Range: -5.1643

Max Act: 4.7893. Min Act: -0.1700

Data Index: 308328 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 5.1643. Min Range: -5.1643

Max Act: 4.7893. Min Act: -0.1700

Data Index: 1179027 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 5.1643. Min Range: -5.1643

Max Act: 4.7893. Min Act: -0.1700

Data Index: 1019475 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 5.1643. Min Range: -5.1643

Max Act: 4.7893. Min Act: -0.1700

Data Index: 1240463 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 5.1643. Min Range: -5.1643

Max Act: 4.7580. Min Act: -0.1700

Data Index: 599911 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 5.1643. Min Range: -5.1643

Max Act: 4.7580. Min Act: -0.1700

Data Index: 136173 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 5.1643. Min Range: -5.1643

Max Act: 4.6955. Min Act: -0.1700

Data Index: 64304 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 5.1643. Min Range: -5.1643

Max Act: 4.7580. Min Act: -0.1700

Data Index: 265658 (C4 (Web Text))

Max Activating Token Index: 253