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

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

Neuron 971 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: 5.7562. Min Range: -5.7562

Max Act: 5.7562. Min Act: -0.1700

Data Index: 858927 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.4437. Min Act: -0.1700

Data Index: 362139 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.3187. Min Act: -0.1699

Data Index: 1293381 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.2874. Min Act: -0.1699

Data Index: 444124 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.2249. Min Act: -0.1700

Data Index: 375822 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.2874. Min Act: -0.1700

Data Index: 65108 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.1937. Min Act: -0.1700

Data Index: 1081992 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.2562. Min Act: -0.1700

Data Index: 613119 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.2562. Min Act: -0.1700

Data Index: 247905 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.1937. Min Act: -0.1700

Data Index: 76495 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.1937. Min Act: -0.1699

Data Index: 835633 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.1937. Min Act: -0.1700

Data Index: 247806 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.1937. Min Act: -0.1697

Data Index: 780023 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.1937. Min Act: -0.1700

Data Index: 785631 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.1624. Min Act: -0.1700

Data Index: 681654 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.1624. Min Act: -0.1700

Data Index: 1064857 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.1312. Min Act: -0.1700

Data Index: 1300242 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.1624. Min Act: -0.1700

Data Index: 699664 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.0687. Min Act: -0.1700

Data Index: 989186 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 5.7562. Min Range: -5.7562

Max Act: 5.0687. Min Act: -0.1700

Data Index: 333130 (C4 (Web Text))

Max Activating Token Index: 696