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

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

Neuron 1284 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: 2.8846. Min Range: -2.8846

Max Act: 2.8846. Min Act: -0.1700

Data Index: 626541 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 2.8846. Min Range: -2.8846

Max Act: 2.8806. Min Act: -0.1700

Data Index: 526780 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 2.8846. Min Range: -2.8846

Max Act: 2.8224. Min Act: -0.1700

Data Index: 202560 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 2.8846. Min Range: -2.8846

Max Act: 2.8239. Min Act: -0.1700

Data Index: 1071236 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 2.8846. Min Range: -2.8846

Max Act: 2.8260. Min Act: -0.1700

Data Index: 1168720 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 2.8846. Min Range: -2.8846

Max Act: 2.8092. Min Act: -0.1700

Data Index: 278362 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 2.8846. Min Range: -2.8846

Max Act: 2.7949. Min Act: -0.1700

Data Index: 1218215 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 2.8846. Min Range: -2.8846

Max Act: 2.7682. Min Act: -0.1700

Data Index: 582041 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 2.8846. Min Range: -2.8846

Max Act: 2.7670. Min Act: -0.1700

Data Index: 956012 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 2.8846. Min Range: -2.8846

Max Act: 2.7843. Min Act: -0.1700

Data Index: 925530 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 2.8846. Min Range: -2.8846

Max Act: 2.7571. Min Act: -0.1700

Data Index: 413235 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 2.8846. Min Range: -2.8846

Max Act: 2.7404. Min Act: -0.1700

Data Index: 353947 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 2.8846. Min Range: -2.8846

Max Act: 2.7338. Min Act: -0.1700

Data Index: 395154 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 2.8846. Min Range: -2.8846

Max Act: 2.7284. Min Act: -0.1700

Data Index: 723317 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 2.8846. Min Range: -2.8846

Max Act: 2.7345. Min Act: -0.1700

Data Index: 439670 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 2.8846. Min Range: -2.8846

Max Act: 2.7074. Min Act: -0.1700

Data Index: 241172 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 2.8846. Min Range: -2.8846

Max Act: 2.7276. Min Act: -0.1700

Data Index: 349833 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 2.8846. Min Range: -2.8846

Max Act: 2.7175. Min Act: -0.1700

Data Index: 821733 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 2.8846. Min Range: -2.8846

Max Act: 2.7228. Min Act: -0.1700

Data Index: 840158 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 2.8846. Min Range: -2.8846

Max Act: 2.7335. Min Act: -0.1700

Data Index: 1034982 (C4 (Web Text))

Max Activating Token Index: 846