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

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

Neuron 280 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: 3.3529. Min Range: -3.3529

Max Act: 3.3529. Min Act: -0.1700

Data Index: 289400 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 3.3529. Min Range: -3.3529

Max Act: 3.3372. Min Act: -0.1700

Data Index: 562090 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 3.3529. Min Range: -3.3529

Max Act: 3.3215. Min Act: -0.1700

Data Index: 625476 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 3.3529. Min Range: -3.3529

Max Act: 3.3058. Min Act: -0.1700

Data Index: 1158150 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 3.3529. Min Range: -3.3529

Max Act: 3.2743. Min Act: -0.1700

Data Index: 1174998 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 3.3529. Min Range: -3.3529

Max Act: 3.2900. Min Act: -0.1700

Data Index: 701521 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 3.3529. Min Range: -3.3529

Max Act: 3.2586. Min Act: -0.1700

Data Index: 270205 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 3.3529. Min Range: -3.3529

Max Act: 3.2586. Min Act: -0.1700

Data Index: 1170630 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 3.3529. Min Range: -3.3529

Max Act: 3.2429. Min Act: -0.1700

Data Index: 576488 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 3.3529. Min Range: -3.3529

Max Act: 3.2429. Min Act: -0.1700

Data Index: 1241453 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 3.3529. Min Range: -3.3529

Max Act: 3.2115. Min Act: -0.1700

Data Index: 687034 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 3.3529. Min Range: -3.3529

Max Act: 3.2115. Min Act: -0.1700

Data Index: 1020573 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 3.3529. Min Range: -3.3529

Max Act: 3.2115. Min Act: -0.1700

Data Index: 900049 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 3.3529. Min Range: -3.3529

Max Act: 3.1642. Min Act: -0.1700

Data Index: 2402 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 3.3529. Min Range: -3.3529

Max Act: 3.1012. Min Act: -0.1700

Data Index: 351585 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 3.3529. Min Range: -3.3529

Max Act: 3.0223. Min Act: -0.1700

Data Index: 1310813 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 3.3529. Min Range: -3.3529

Max Act: 2.9749. Min Act: -0.1700

Data Index: 525945 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 3.3529. Min Range: -3.3529

Max Act: 2.9591. Min Act: -0.1700

Data Index: 686000 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 3.3529. Min Range: -3.3529

Max Act: 2.9432. Min Act: -0.1700

Data Index: 55131 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 3.3529. Min Range: -3.3529

Max Act: 2.9432. Min Act: -0.1700

Data Index: 1215980 (C4 (Web Text))

Max Activating Token Index: 618