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

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

Neuron 1522 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: 4.0211. Min Range: -4.0211

Max Act: 4.0211. Min Act: -0.1623

Data Index: 1194612 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.9951. Min Act: -0.1700

Data Index: 924967 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.9990. Min Act: -0.1700

Data Index: 1069512 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.9360. Min Act: -0.1700

Data Index: 427069 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.9225. Min Act: -0.1700

Data Index: 817037 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.9290. Min Act: -0.1700

Data Index: 1465 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.9069. Min Act: -0.1700

Data Index: 582688 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8958. Min Act: -0.1700

Data Index: 1347272 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8593. Min Act: -0.1700

Data Index: 768009 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8846. Min Act: -0.1700

Data Index: 421579 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8928. Min Act: -0.1700

Data Index: 163125 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8615. Min Act: -0.1700

Data Index: 1207821 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8576. Min Act: -0.1700

Data Index: 493749 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8715. Min Act: -0.1700

Data Index: 1085999 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8684. Min Act: -0.1700

Data Index: 747447 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8296. Min Act: -0.1700

Data Index: 598751 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8431. Min Act: -0.1666

Data Index: 1234715 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8282. Min Act: -0.1700

Data Index: 134695 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8467. Min Act: -0.1700

Data Index: 326842 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8065. Min Act: -0.1694

Data Index: 105786 (C4 (Web Text))

Max Activating Token Index: 881