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

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

Neuron 1580 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: 3.2106. Min Range: -3.2106

Max Act: 3.2106. Min Act: -0.1700

Data Index: 549254 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 3.2106. Min Range: -3.2106

Max Act: 3.0688. Min Act: -0.1700

Data Index: 1194041 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 3.2106. Min Range: -3.2106

Max Act: 3.0416. Min Act: -0.1700

Data Index: 627053 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 3.2106. Min Range: -3.2106

Max Act: 3.0193. Min Act: -0.1700

Data Index: 512276 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 3.2106. Min Range: -3.2106

Max Act: 2.9839. Min Act: -0.1700

Data Index: 1240169 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 3.2106. Min Range: -3.2106

Max Act: 2.9901. Min Act: -0.1700

Data Index: 941320 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 3.2106. Min Range: -3.2106

Max Act: 2.9657. Min Act: -0.1700

Data Index: 1241386 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 3.2106. Min Range: -3.2106

Max Act: 2.9694. Min Act: -0.1700

Data Index: 324059 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 3.2106. Min Range: -3.2106

Max Act: 2.9409. Min Act: -0.1700

Data Index: 240468 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 3.2106. Min Range: -3.2106

Max Act: 2.9577. Min Act: -0.1700

Data Index: 57797 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 3.2106. Min Range: -3.2106

Max Act: 2.9459. Min Act: -0.1700

Data Index: 502124 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 3.2106. Min Range: -3.2106

Max Act: 2.9232. Min Act: -0.1700

Data Index: 1013430 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 3.2106. Min Range: -3.2106

Max Act: 2.9412. Min Act: -0.1700

Data Index: 731972 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 3.2106. Min Range: -3.2106

Max Act: 2.8984. Min Act: -0.1700

Data Index: 407570 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 3.2106. Min Range: -3.2106

Max Act: 2.9323. Min Act: -0.1700

Data Index: 1292970 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 3.2106. Min Range: -3.2106

Max Act: 2.9244. Min Act: -0.1700

Data Index: 912895 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 3.2106. Min Range: -3.2106

Max Act: 2.9006. Min Act: -0.1700

Data Index: 484474 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 3.2106. Min Range: -3.2106

Max Act: 2.9040. Min Act: -0.1700

Data Index: 1358855 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 3.2106. Min Range: -3.2106

Max Act: 2.8745. Min Act: -0.1700

Data Index: 306768 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 3.2106. Min Range: -3.2106

Max Act: 2.8858. Min Act: -0.1700

Data Index: 41135 (C4 (Web Text))

Max Activating Token Index: 632