Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 978 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.6409. Min Act: -0.1700

Data Index: 658702 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.3275. Min Act: -0.1700

Data Index: 479211 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.3432. Min Act: -0.1700

Data Index: 632135 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.3118. Min Act: -0.1700

Data Index: 148038 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.3118. Min Act: -0.1700

Data Index: 861001 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.2646. Min Act: -0.1700

Data Index: 1517762 (Python Code)

Max Activating Token Index: 372

Text #6

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.2489. Min Act: -0.1700

Data Index: 1310724 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.2646. Min Act: -0.1700

Data Index: 1129001 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.2332. Min Act: -0.1700

Data Index: 450170 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.2175. Min Act: -0.1700

Data Index: 1338087 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.1703. Min Act: -0.1700

Data Index: 1248607 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.2017. Min Act: -0.1700

Data Index: 451290 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.1230. Min Act: -0.1700

Data Index: 94817 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.1703. Min Act: -0.1700

Data Index: 969929 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.1703. Min Act: -0.1700

Data Index: 723711 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.1230. Min Act: -0.1700

Data Index: 1200220 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.1545. Min Act: -0.1700

Data Index: 716053 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.1230. Min Act: -0.1700

Data Index: 371376 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.1230. Min Act: -0.1700

Data Index: 924517 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 3.6409. Min Range: -3.6409

Max Act: 3.1703. Min Act: -0.1700

Data Index: 376871 (C4 (Web Text))

Max Activating Token Index: 44