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

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

Neuron 1148 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: 3.2642. Min Range: -3.2642

Max Act: 3.2642. Min Act: -0.1700

Data Index: 84415 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.1400. Min Act: -0.1700

Data Index: 987104 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.1165. Min Act: -0.1700

Data Index: 882458 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.1327. Min Act: -0.1700

Data Index: 454496 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.0937. Min Act: -0.1700

Data Index: 712343 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.0881. Min Act: -0.1700

Data Index: 1111021 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.0602. Min Act: -0.1700

Data Index: 1117233 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.0537. Min Act: -0.1700

Data Index: 1071721 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.0489. Min Act: -0.1700

Data Index: 77854 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.0414. Min Act: -0.1700

Data Index: 19394 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.0348. Min Act: -0.1700

Data Index: 1356069 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 3.2642. Min Range: -3.2642

Max Act: 2.9989. Min Act: -0.1700

Data Index: 754812 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 3.2642. Min Range: -3.2642

Max Act: 2.9923. Min Act: -0.1700

Data Index: 461383 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 3.2642. Min Range: -3.2642

Max Act: 2.9964. Min Act: -0.1700

Data Index: 1518775 (Python Code)

Max Activating Token Index: 15

Text #14

Max Range: 3.2642. Min Range: -3.2642

Max Act: 2.9885. Min Act: -0.1700

Data Index: 371863 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 3.2642. Min Range: -3.2642

Max Act: 2.9968. Min Act: -0.1700

Data Index: 388647 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 3.2642. Min Range: -3.2642

Max Act: 2.9783. Min Act: -0.1700

Data Index: 1168990 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 3.2642. Min Range: -3.2642

Max Act: 2.9854. Min Act: -0.1700

Data Index: 236786 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 3.2642. Min Range: -3.2642

Max Act: 2.9788. Min Act: -0.1700

Data Index: 741007 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 3.2642. Min Range: -3.2642

Max Act: 2.9928. Min Act: -0.1700

Data Index: 996270 (C4 (Web Text))

Max Activating Token Index: 809