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

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

Neuron 1377 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.3355. Min Act: -0.1700

Data Index: 1333217 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.3355. Min Act: -0.1700

Data Index: 703459 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.3198. Min Act: -0.1700

Data Index: 826214 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.2884. Min Act: -0.1700

Data Index: 927538 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.2727. Min Act: -0.1700

Data Index: 1002871 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.2570. Min Act: -0.1700

Data Index: 934833 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.2884. Min Act: -0.1700

Data Index: 912671 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.2727. Min Act: -0.1700

Data Index: 1017482 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.2727. Min Act: -0.1700

Data Index: 855235 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.2884. Min Act: -0.1700

Data Index: 493776 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.2570. Min Act: -0.1700

Data Index: 843887 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.1941. Min Act: -0.1700

Data Index: 137359 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.2413. Min Act: -0.1700

Data Index: 168664 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.2256. Min Act: -0.1700

Data Index: 360415 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.2098. Min Act: -0.1700

Data Index: 331315 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.2098. Min Act: -0.1700

Data Index: 1212465 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.2256. Min Act: -0.1700

Data Index: 363391 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.2098. Min Act: -0.1700

Data Index: 710700 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.1941. Min Act: -0.1700

Data Index: 722180 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 3.3355. Min Range: -3.3355

Max Act: 3.2256. Min Act: -0.1700

Data Index: 1311138 (C4 (Web Text))

Max Activating Token Index: 766