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

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

Neuron 1776 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.6130. Min Act: -0.1699

Data Index: 1196659 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.6130. Min Act: -0.1632

Data Index: 213424 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.6130. Min Act: -0.1663

Data Index: 356239 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.5505. Min Act: -0.1700

Data Index: 586832 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.5505. Min Act: -0.1700

Data Index: 1017208 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.5505. Min Act: -0.1700

Data Index: 963114 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.4880. Min Act: -0.1699

Data Index: 172139 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.4568. Min Act: -0.1700

Data Index: 1221258 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.4880. Min Act: -0.1700

Data Index: 447061 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.4255. Min Act: -0.1700

Data Index: 1062580 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.4880. Min Act: -0.1699

Data Index: 387328 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.4255. Min Act: -0.1700

Data Index: 875625 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.4255. Min Act: -0.1661

Data Index: 1107641 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.4255. Min Act: -0.1699

Data Index: 1221619 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.3943. Min Act: -0.1700

Data Index: 320304 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.3943. Min Act: -0.1212

Data Index: 196103 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.3943. Min Act: -0.1700

Data Index: 961050 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.3943. Min Act: -0.1700

Data Index: 132263 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.3943. Min Act: -0.1700

Data Index: 1211661 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 5.6130. Min Range: -5.6130

Max Act: 5.3630. Min Act: -0.1700

Data Index: 554257 (C4 (Web Text))

Max Activating Token Index: 646