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

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

Neuron 365 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: 2.8641. Min Range: -2.8641

Max Act: 2.8641. Min Act: -0.1700

Data Index: 1443532 (Python Code)

Max Activating Token Index: 90

Text #1

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.8179. Min Act: -0.1700

Data Index: 1382606 (Python Code)

Max Activating Token Index: 31

Text #2

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.8223. Min Act: -0.1700

Data Index: 1023911 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.7613. Min Act: -0.1700

Data Index: 763900 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.7363. Min Act: -0.1700

Data Index: 598168 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.7345. Min Act: -0.1700

Data Index: 226436 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.7265. Min Act: -0.1700

Data Index: 945665 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.6969. Min Act: -0.1700

Data Index: 1266322 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.7057. Min Act: -0.1700

Data Index: 1426517 (Python Code)

Max Activating Token Index: 176

Text #9

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.7318. Min Act: -0.1700

Data Index: 810220 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.7249. Min Act: -0.1700

Data Index: 531216 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.6911. Min Act: -0.1700

Data Index: 95171 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.7056. Min Act: -0.1700

Data Index: 1587180 (Python Code)

Max Activating Token Index: 26

Text #13

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.7067. Min Act: -0.1700

Data Index: 1073108 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.6846. Min Act: -0.1700

Data Index: 267804 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.6807. Min Act: -0.1700

Data Index: 1239643 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.6702. Min Act: -0.1700

Data Index: 1381541 (Python Code)

Max Activating Token Index: 428

Text #17

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.6538. Min Act: -0.1700

Data Index: 1205639 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.6533. Min Act: -0.1700

Data Index: 231572 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.6737. Min Act: -0.1700

Data Index: 996698 (C4 (Web Text))

Max Activating Token Index: 755