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

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

Neuron 514 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2356. Min Range: -3.2356

Max Act: 3.2356. Min Act: -0.1700

Data Index: 661365 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 3.2356. Min Range: -3.2356

Max Act: 3.2199. Min Act: -0.1700

Data Index: 835783 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 3.2356. Min Range: -3.2356

Max Act: 3.1570. Min Act: -0.1700

Data Index: 617919 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 3.2356. Min Range: -3.2356

Max Act: 3.1570. Min Act: -0.1700

Data Index: 175568 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 3.2356. Min Range: -3.2356

Max Act: 3.1255. Min Act: -0.1700

Data Index: 1055839 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 3.2356. Min Range: -3.2356

Max Act: 3.1097. Min Act: -0.1700

Data Index: 322375 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 3.2356. Min Range: -3.2356

Max Act: 3.1097. Min Act: -0.1700

Data Index: 271625 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 3.2356. Min Range: -3.2356

Max Act: 3.0939. Min Act: -0.1700

Data Index: 1001855 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 3.2356. Min Range: -3.2356

Max Act: 3.0939. Min Act: -0.1699

Data Index: 1359158 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 3.2356. Min Range: -3.2356

Max Act: 3.0939. Min Act: -0.1700

Data Index: 1328173 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 3.2356. Min Range: -3.2356

Max Act: 3.0782. Min Act: -0.1700

Data Index: 726378 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 3.2356. Min Range: -3.2356

Max Act: 3.0308. Min Act: -0.1700

Data Index: 1133126 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 3.2356. Min Range: -3.2356

Max Act: 3.0308. Min Act: -0.1700

Data Index: 908760 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 3.2356. Min Range: -3.2356

Max Act: 3.0150. Min Act: -0.1700

Data Index: 905258 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 3.2356. Min Range: -3.2356

Max Act: 3.0308. Min Act: -0.1700

Data Index: 1004646 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 3.2356. Min Range: -3.2356

Max Act: 2.9992. Min Act: -0.1700

Data Index: 680134 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 3.2356. Min Range: -3.2356

Max Act: 2.9834. Min Act: -0.1700

Data Index: 886601 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 3.2356. Min Range: -3.2356

Max Act: 2.9676. Min Act: -0.1700

Data Index: 101565 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 3.2356. Min Range: -3.2356

Max Act: 2.9676. Min Act: -0.1700

Data Index: 1132185 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 3.2356. Min Range: -3.2356

Max Act: 2.9517. Min Act: -0.1700

Data Index: 44162 (C4 (Web Text))

Max Activating Token Index: 411