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

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

Neuron 939 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: 4.1377. Min Range: -4.1377

Max Act: 4.1377. Min Act: -0.1700

Data Index: 1469372 (Python Code)

Max Activating Token Index: 215

Text #1

Max Range: 4.1377. Min Range: -4.1377

Max Act: 4.0808. Min Act: -0.1700

Data Index: 1414022 (Python Code)

Max Activating Token Index: 425

Text #2

Max Range: 4.1377. Min Range: -4.1377

Max Act: 4.0774. Min Act: -0.1700

Data Index: 678562 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 4.1377. Min Range: -4.1377

Max Act: 4.0587. Min Act: -0.1700

Data Index: 1475909 (Python Code)

Max Activating Token Index: 548

Text #4

Max Range: 4.1377. Min Range: -4.1377

Max Act: 4.0569. Min Act: -0.1700

Data Index: 1390563 (Python Code)

Max Activating Token Index: 225

Text #5

Max Range: 4.1377. Min Range: -4.1377

Max Act: 4.0447. Min Act: -0.1700

Data Index: 1469593 (Python Code)

Max Activating Token Index: 313

Text #6

Max Range: 4.1377. Min Range: -4.1377

Max Act: 4.0190. Min Act: -0.1700

Data Index: 1470777 (Python Code)

Max Activating Token Index: 182

Text #7

Max Range: 4.1377. Min Range: -4.1377

Max Act: 4.0311. Min Act: -0.1700

Data Index: 1404229 (Python Code)

Max Activating Token Index: 812

Text #8

Max Range: 4.1377. Min Range: -4.1377

Max Act: 4.0096. Min Act: -0.1700

Data Index: 1467594 (Python Code)

Max Activating Token Index: 844

Text #9

Max Range: 4.1377. Min Range: -4.1377

Max Act: 3.9727. Min Act: -0.1700

Data Index: 1368853 (Python Code)

Max Activating Token Index: 398

Text #10

Max Range: 4.1377. Min Range: -4.1377

Max Act: 3.9672. Min Act: -0.1700

Data Index: 1504036 (Python Code)

Max Activating Token Index: 582

Text #11

Max Range: 4.1377. Min Range: -4.1377

Max Act: 3.9514. Min Act: -0.1700

Data Index: 1539905 (Python Code)

Max Activating Token Index: 682

Text #12

Max Range: 4.1377. Min Range: -4.1377

Max Act: 3.9443. Min Act: -0.1700

Data Index: 1588995 (Python Code)

Max Activating Token Index: 80

Text #13

Max Range: 4.1377. Min Range: -4.1377

Max Act: 3.9154. Min Act: -0.1700

Data Index: 1395503 (Python Code)

Max Activating Token Index: 197

Text #14

Max Range: 4.1377. Min Range: -4.1377

Max Act: 3.8929. Min Act: -0.1700

Data Index: 1521496 (Python Code)

Max Activating Token Index: 536

Text #15

Max Range: 4.1377. Min Range: -4.1377

Max Act: 3.8297. Min Act: -0.1700

Data Index: 1495315 (Python Code)

Max Activating Token Index: 900

Text #16

Max Range: 4.1377. Min Range: -4.1377

Max Act: 3.8909. Min Act: -0.1700

Data Index: 1444974 (Python Code)

Max Activating Token Index: 320

Text #17

Max Range: 4.1377. Min Range: -4.1377

Max Act: 3.8898. Min Act: -0.1700

Data Index: 1593017 (Python Code)

Max Activating Token Index: 164

Text #18

Max Range: 4.1377. Min Range: -4.1377

Max Act: 3.8662. Min Act: -0.1700

Data Index: 1415147 (Python Code)

Max Activating Token Index: 817

Text #19

Max Range: 4.1377. Min Range: -4.1377

Max Act: 3.8848. Min Act: -0.1700

Data Index: 1506256 (Python Code)

Max Activating Token Index: 685