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

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

Neuron 1548 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: 3.6653. Min Range: -3.6653

Max Act: 3.6653. Min Act: -0.1700

Data Index: 491025 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.3362. Min Act: -0.1700

Data Index: 191144 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.2577. Min Act: -0.1700

Data Index: 633218 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.2420. Min Act: -0.1700

Data Index: 1321548 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.2577. Min Act: -0.1700

Data Index: 366319 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.2105. Min Act: -0.1700

Data Index: 906717 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.1791. Min Act: -0.1700

Data Index: 1239188 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.2105. Min Act: -0.1700

Data Index: 1082475 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.2105. Min Act: -0.1700

Data Index: 344359 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.1948. Min Act: -0.1700

Data Index: 1327425 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.1791. Min Act: -0.1700

Data Index: 275534 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.1791. Min Act: -0.1700

Data Index: 944334 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.1791. Min Act: -0.1700

Data Index: 654483 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.1791. Min Act: -0.1700

Data Index: 1072054 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.1791. Min Act: -0.1700

Data Index: 526014 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.1791. Min Act: -0.1700

Data Index: 1358459 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.1633. Min Act: -0.1700

Data Index: 592559 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.1476. Min Act: -0.1700

Data Index: 723488 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.1476. Min Act: -0.1700

Data Index: 240474 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.1633. Min Act: -0.1700

Data Index: 924384 (C4 (Web Text))

Max Activating Token Index: 943