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

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

Neuron 1632 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: 3.9847. Min Range: -3.9847

Max Act: 3.9847. Min Act: -0.1700

Data Index: 727901 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 3.9847. Min Range: -3.9847

Max Act: 3.8909. Min Act: -0.1700

Data Index: 562654 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 3.9847. Min Range: -3.9847

Max Act: 3.7971. Min Act: -0.1700

Data Index: 1308694 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 3.9847. Min Range: -3.9847

Max Act: 3.7345. Min Act: -0.1700

Data Index: 1258606 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 3.9847. Min Range: -3.9847

Max Act: 3.7345. Min Act: -0.1700

Data Index: 57758 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 3.9847. Min Range: -3.9847

Max Act: 3.7345. Min Act: -0.1700

Data Index: 84646 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 3.9847. Min Range: -3.9847

Max Act: 3.7032. Min Act: -0.1700

Data Index: 100824 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 3.9847. Min Range: -3.9847

Max Act: 3.7345. Min Act: -0.1700

Data Index: 1214262 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 3.9847. Min Range: -3.9847

Max Act: 3.6719. Min Act: -0.1700

Data Index: 242266 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 3.9847. Min Range: -3.9847

Max Act: 3.7032. Min Act: -0.1700

Data Index: 543901 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 3.9847. Min Range: -3.9847

Max Act: 3.6719. Min Act: -0.1700

Data Index: 346835 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 3.9847. Min Range: -3.9847

Max Act: 3.6406. Min Act: -0.1700

Data Index: 448920 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 3.9847. Min Range: -3.9847

Max Act: 3.6719. Min Act: -0.1700

Data Index: 649332 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 3.9847. Min Range: -3.9847

Max Act: 3.6093. Min Act: -0.1700

Data Index: 1173610 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 3.9847. Min Range: -3.9847

Max Act: 3.6406. Min Act: -0.1700

Data Index: 592923 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 3.9847. Min Range: -3.9847

Max Act: 3.6093. Min Act: -0.1700

Data Index: 493314 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 3.9847. Min Range: -3.9847

Max Act: 3.6093. Min Act: -0.1698

Data Index: 974918 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 3.9847. Min Range: -3.9847

Max Act: 3.6719. Min Act: -0.1700

Data Index: 889919 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 3.9847. Min Range: -3.9847

Max Act: 3.6406. Min Act: -0.1700

Data Index: 296567 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 3.9847. Min Range: -3.9847

Max Act: 3.6093. Min Act: -0.1700

Data Index: 369923 (C4 (Web Text))

Max Activating Token Index: 694