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

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

Neuron 1508 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: 4.9644. Min Range: -4.9644

Max Act: 4.9088. Min Act: -0.1699

Data Index: 641430 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 4.9644. Min Range: -4.9644

Max Act: 4.9445. Min Act: -0.1700

Data Index: 1165521 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 4.9644. Min Range: -4.9644

Max Act: 4.9644. Min Act: -0.1700

Data Index: 518637 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 4.9644. Min Range: -4.9644

Max Act: 4.8789. Min Act: -0.1700

Data Index: 1324782 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 4.9644. Min Range: -4.9644

Max Act: 4.8958. Min Act: -0.1700

Data Index: 1164154 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 4.9644. Min Range: -4.9644

Max Act: 4.8897. Min Act: -0.1700

Data Index: 849163 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 4.9644. Min Range: -4.9644

Max Act: 4.7876. Min Act: -0.1700

Data Index: 1342576 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 4.9644. Min Range: -4.9644

Max Act: 4.7925. Min Act: -0.1699

Data Index: 829264 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 4.9644. Min Range: -4.9644

Max Act: 4.8071. Min Act: -0.1700

Data Index: 869639 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 4.9644. Min Range: -4.9644

Max Act: 4.8041. Min Act: -0.1699

Data Index: 492411 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 4.9644. Min Range: -4.9644

Max Act: 4.8111. Min Act: -0.1700

Data Index: 554437 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 4.9644. Min Range: -4.9644

Max Act: 4.8151. Min Act: -0.1699

Data Index: 961036 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 4.9644. Min Range: -4.9644

Max Act: 4.7439. Min Act: -0.1700

Data Index: 227411 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 4.9644. Min Range: -4.9644

Max Act: 4.7269. Min Act: -0.1700

Data Index: 490979 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 4.9644. Min Range: -4.9644

Max Act: 4.7601. Min Act: -0.1700

Data Index: 865480 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 4.9644. Min Range: -4.9644

Max Act: 4.7655. Min Act: -0.1700

Data Index: 494466 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 4.9644. Min Range: -4.9644

Max Act: 4.7642. Min Act: -0.1700

Data Index: 203544 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 4.9644. Min Range: -4.9644

Max Act: 4.7638. Min Act: -0.1698

Data Index: 535585 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 4.9644. Min Range: -4.9644

Max Act: 4.7397. Min Act: -0.1700

Data Index: 547062 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 4.9644. Min Range: -4.9644

Max Act: 4.7335. Min Act: -0.1676

Data Index: 899151 (C4 (Web Text))

Max Activating Token Index: 97