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

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

Neuron 1885 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.8099. Min Act: -0.1700

Data Index: 299595 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.8412. Min Act: -0.1700

Data Index: 805454 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.6537. Min Act: -0.1700

Data Index: 172233 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.7474. Min Act: -0.1700

Data Index: 506471 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.6537. Min Act: -0.1700

Data Index: 329027 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.5912. Min Act: -0.1700

Data Index: 159079 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.6537. Min Act: -0.1700

Data Index: 862056 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.5912. Min Act: -0.1700

Data Index: 1050133 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.5912. Min Act: -0.1700

Data Index: 142595 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.6849. Min Act: -0.1700

Data Index: 652414 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.5912. Min Act: -0.1700

Data Index: 281517 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.5912. Min Act: -0.1700

Data Index: 591345 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.5599. Min Act: -0.1700

Data Index: 905341 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.5912. Min Act: -0.1700

Data Index: 1015551 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.5599. Min Act: -0.1699

Data Index: 1081268 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.5287. Min Act: -0.1700

Data Index: 1308564 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.5599. Min Act: -0.1700

Data Index: 540936 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.5912. Min Act: -0.1700

Data Index: 994115 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.5287. Min Act: -0.1700

Data Index: 714698 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 5.8412. Min Range: -5.8412

Max Act: 5.4974. Min Act: -0.1700

Data Index: 797525 (C4 (Web Text))

Max Activating Token Index: 637