Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 611 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.3906. Min Act: -0.1700

Data Index: 110649 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.3298. Min Act: -0.1700

Data Index: 1213781 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.3215. Min Act: -0.1700

Data Index: 1251310 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.3063. Min Act: -0.1700

Data Index: 7632 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.3025. Min Act: -0.1700

Data Index: 705067 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2819. Min Act: -0.1700

Data Index: 644086 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2744. Min Act: -0.1700

Data Index: 616117 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2647. Min Act: -0.1700

Data Index: 11535 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2588. Min Act: -0.1700

Data Index: 729756 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2308. Min Act: -0.1700

Data Index: 434824 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2633. Min Act: -0.1700

Data Index: 1163213 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2389. Min Act: -0.1700

Data Index: 587118 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2290. Min Act: -0.1700

Data Index: 24585 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.1854. Min Act: -0.1700

Data Index: 605913 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2240. Min Act: -0.1700

Data Index: 571728 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2181. Min Act: -0.1700

Data Index: 774171 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2240. Min Act: -0.1700

Data Index: 734289 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.1811. Min Act: -0.1700

Data Index: 1136430 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.1929. Min Act: -0.1700

Data Index: 254886 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.1938. Min Act: -0.1700

Data Index: 1306875 (C4 (Web Text))

Max Activating Token Index: 537