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

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

Neuron 1338 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.1304. Min Act: -0.1700

Data Index: 969622 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.1304. Min Act: -0.1700

Data Index: 545284 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.1461. Min Act: -0.1700

Data Index: 203457 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.1146. Min Act: -0.1700

Data Index: 986319 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0831. Min Act: -0.1700

Data Index: 1156511 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0988. Min Act: -0.1700

Data Index: 554586 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0831. Min Act: -0.1700

Data Index: 415837 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0831. Min Act: -0.1700

Data Index: 1089216 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0831. Min Act: -0.1700

Data Index: 91346 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0988. Min Act: -0.1700

Data Index: 444053 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0831. Min Act: -0.1700

Data Index: 1252196 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0988. Min Act: -0.1700

Data Index: 294006 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0831. Min Act: -0.1700

Data Index: 496945 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0673. Min Act: -0.1700

Data Index: 1124842 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0673. Min Act: -0.1700

Data Index: 1138450 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0515. Min Act: -0.1700

Data Index: 605276 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0673. Min Act: -0.1700

Data Index: 392902 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0515. Min Act: -0.1700

Data Index: 1146771 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0515. Min Act: -0.1700

Data Index: 229672 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0673. Min Act: -0.1700

Data Index: 834122 (C4 (Web Text))

Max Activating Token Index: 156