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

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

Neuron 133 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: 3.8969. Min Range: -3.8969

Max Act: 3.8969. Min Act: -0.1700

Data Index: 924998 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 3.8969. Min Range: -3.8969

Max Act: 3.8327. Min Act: -0.1700

Data Index: 813648 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 3.8969. Min Range: -3.8969

Max Act: 3.8223. Min Act: -0.1700

Data Index: 1213180 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 3.8969. Min Range: -3.8969

Max Act: 3.8465. Min Act: -0.1700

Data Index: 1106683 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 3.8969. Min Range: -3.8969

Max Act: 3.7693. Min Act: -0.1700

Data Index: 438572 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 3.8969. Min Range: -3.8969

Max Act: 3.7524. Min Act: -0.1700

Data Index: 1325728 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 3.8969. Min Range: -3.8969

Max Act: 3.7363. Min Act: -0.1700

Data Index: 1054565 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 3.8969. Min Range: -3.8969

Max Act: 3.7122. Min Act: -0.1700

Data Index: 856205 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 3.8969. Min Range: -3.8969

Max Act: 3.7184. Min Act: -0.1700

Data Index: 747769 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 3.8969. Min Range: -3.8969

Max Act: 3.7069. Min Act: -0.1700

Data Index: 837937 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 3.8969. Min Range: -3.8969

Max Act: 3.6829. Min Act: -0.1700

Data Index: 426184 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 3.8969. Min Range: -3.8969

Max Act: 3.6955. Min Act: -0.1700

Data Index: 957563 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 3.8969. Min Range: -3.8969

Max Act: 3.6580. Min Act: -0.1700

Data Index: 1164152 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 3.8969. Min Range: -3.8969

Max Act: 3.6343. Min Act: -0.1700

Data Index: 1206294 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 3.8969. Min Range: -3.8969

Max Act: 3.6450. Min Act: -0.1700

Data Index: 1164865 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 3.8969. Min Range: -3.8969

Max Act: 3.6182. Min Act: -0.1700

Data Index: 494461 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 3.8969. Min Range: -3.8969

Max Act: 3.6169. Min Act: -0.1700

Data Index: 198861 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 3.8969. Min Range: -3.8969

Max Act: 3.6390. Min Act: -0.1700

Data Index: 780413 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 3.8969. Min Range: -3.8969

Max Act: 3.6209. Min Act: -0.1700

Data Index: 662517 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 3.8969. Min Range: -3.8969

Max Act: 3.6076. Min Act: -0.1700

Data Index: 1279254 (C4 (Web Text))

Max Activating Token Index: 506