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

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

Neuron 1269 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: 3.4209. Min Range: -3.4209

Max Act: 3.4209. Min Act: -0.1700

Data Index: 673364 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.4205. Min Act: -0.1700

Data Index: 725057 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.2453. Min Act: -0.1700

Data Index: 505261 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.1947. Min Act: -0.1700

Data Index: 1639431 (Python Code)

Max Activating Token Index: 19

Text #4

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.1349. Min Act: -0.1700

Data Index: 480658 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.1309. Min Act: -0.1700

Data Index: 1056236 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.1275. Min Act: -0.1700

Data Index: 1013720 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.1222. Min Act: -0.1700

Data Index: 564496 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.1292. Min Act: -0.1700

Data Index: 34778 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.1075. Min Act: -0.1700

Data Index: 324024 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.0921. Min Act: -0.1700

Data Index: 1144993 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.0983. Min Act: -0.1700

Data Index: 168383 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.0990. Min Act: -0.1700

Data Index: 271169 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.0977. Min Act: -0.1700

Data Index: 608468 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.0845. Min Act: -0.1699

Data Index: 356744 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.0876. Min Act: -0.1700

Data Index: 1134702 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.0966. Min Act: -0.1700

Data Index: 1313418 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.0950. Min Act: -0.1700

Data Index: 503057 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.0776. Min Act: -0.1700

Data Index: 793964 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 3.4209. Min Range: -3.4209

Max Act: 3.0779. Min Act: -0.1700

Data Index: 367989 (C4 (Web Text))

Max Activating Token Index: 794