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

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

Neuron 833 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.4904. Min Range: -4.4904

Max Act: 4.4904. Min Act: -0.1700

Data Index: 70273 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 4.4904. Min Range: -4.4904

Max Act: 4.3341. Min Act: -0.1700

Data Index: 462079 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 4.4904. Min Range: -4.4904

Max Act: 4.1466. Min Act: -0.1700

Data Index: 1287514 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 4.4904. Min Range: -4.4904

Max Act: 4.1309. Min Act: -0.1700

Data Index: 902251 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 4.4904. Min Range: -4.4904

Max Act: 4.0841. Min Act: -0.1691

Data Index: 889893 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 4.4904. Min Range: -4.4904

Max Act: 4.1153. Min Act: -0.1700

Data Index: 733808 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 4.4904. Min Range: -4.4904

Max Act: 4.0215. Min Act: -0.1700

Data Index: 745774 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 4.4904. Min Range: -4.4904

Max Act: 4.0059. Min Act: -0.1700

Data Index: 1016682 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 4.4904. Min Range: -4.4904

Max Act: 3.9903. Min Act: -0.1700

Data Index: 222777 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 4.4904. Min Range: -4.4904

Max Act: 4.0372. Min Act: -0.1700

Data Index: 1081170 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 4.4904. Min Range: -4.4904

Max Act: 3.9590. Min Act: -0.1700

Data Index: 737237 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 4.4904. Min Range: -4.4904

Max Act: 3.9434. Min Act: -0.1700

Data Index: 1189668 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 4.4904. Min Range: -4.4904

Max Act: 3.8808. Min Act: -0.1700

Data Index: 638127 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 4.4904. Min Range: -4.4904

Max Act: 3.8652. Min Act: -0.1700

Data Index: 489889 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 4.4904. Min Range: -4.4904

Max Act: 3.9277. Min Act: -0.1700

Data Index: 243772 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 4.4904. Min Range: -4.4904

Max Act: 3.8652. Min Act: -0.1700

Data Index: 1240437 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 4.4904. Min Range: -4.4904

Max Act: 3.8652. Min Act: -0.1700

Data Index: 1003310 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 4.4904. Min Range: -4.4904

Max Act: 3.8026. Min Act: -0.1700

Data Index: 764464 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 4.4904. Min Range: -4.4904

Max Act: 3.8026. Min Act: -0.1700

Data Index: 417566 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 4.4904. Min Range: -4.4904

Max Act: 3.7870. Min Act: -0.1700

Data Index: 776576 (C4 (Web Text))

Max Activating Token Index: 577