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

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

Neuron 746 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 8.0091. Min Range: -8.0091

Max Act: 8.0091. Min Act: -0.1699

Data Index: 1030419 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 8.0091. Min Range: -8.0091

Max Act: 7.7591. Min Act: -0.1700

Data Index: 360244 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 8.0091. Min Range: -8.0091

Max Act: 7.4466. Min Act: -0.1700

Data Index: 965654 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 8.0091. Min Range: -8.0091

Max Act: 7.4466. Min Act: -0.1700

Data Index: 146745 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 8.0091. Min Range: -8.0091

Max Act: 7.3841. Min Act: -0.1700

Data Index: 21733 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 8.0091. Min Range: -8.0091

Max Act: 7.3841. Min Act: -0.1700

Data Index: 157483 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 8.0091. Min Range: -8.0091

Max Act: 7.2591. Min Act: -0.1438

Data Index: 1255791 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 8.0091. Min Range: -8.0091

Max Act: 7.1966. Min Act: -0.1700

Data Index: 463266 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 8.0091. Min Range: -8.0091

Max Act: 7.1341. Min Act: -0.1700

Data Index: 314420 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 8.0091. Min Range: -8.0091

Max Act: 7.0716. Min Act: -0.1700

Data Index: 1043368 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 8.0091. Min Range: -8.0091

Max Act: 6.9779. Min Act: -0.1700

Data Index: 528171 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 8.0091. Min Range: -8.0091

Max Act: 6.9466. Min Act: -0.1549

Data Index: 851940 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 8.0091. Min Range: -8.0091

Max Act: 6.9154. Min Act: -0.1700

Data Index: 1296059 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 8.0091. Min Range: -8.0091

Max Act: 6.9154. Min Act: -0.1625

Data Index: 1298159 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 8.0091. Min Range: -8.0091

Max Act: 6.8529. Min Act: -0.1634

Data Index: 478271 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 8.0091. Min Range: -8.0091

Max Act: 6.8216. Min Act: -0.1694

Data Index: 429778 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 8.0091. Min Range: -8.0091

Max Act: 6.8529. Min Act: -0.1700

Data Index: 99806 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 8.0091. Min Range: -8.0091

Max Act: 6.8529. Min Act: -0.1700

Data Index: 272365 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 8.0091. Min Range: -8.0091

Max Act: 6.8529. Min Act: -0.1696

Data Index: 129834 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 8.0091. Min Range: -8.0091

Max Act: 6.8529. Min Act: -0.1676

Data Index: 374992 (C4 (Web Text))

Max Activating Token Index: 406