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

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

Neuron 1498 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: 3.8194. Min Range: -3.8194

Max Act: 3.8194. Min Act: -0.1700

Data Index: 1610047 (Python Code)

Max Activating Token Index: 832

Text #1

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.6645. Min Act: -0.1700

Data Index: 1187873 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4768. Min Act: -0.1700

Data Index: 1655867 (Python Code)

Max Activating Token Index: 173

Text #3

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4771. Min Act: -0.1700

Data Index: 1149814 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4694. Min Act: -0.1700

Data Index: 1630812 (Python Code)

Max Activating Token Index: 242

Text #5

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4582. Min Act: -0.1700

Data Index: 1372946 (Python Code)

Max Activating Token Index: 388

Text #6

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4483. Min Act: -0.1700

Data Index: 1470850 (Python Code)

Max Activating Token Index: 235

Text #7

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4222. Min Act: -0.1700

Data Index: 1553391 (Python Code)

Max Activating Token Index: 996

Text #8

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4083. Min Act: -0.1700

Data Index: 1400483 (Python Code)

Max Activating Token Index: 1018

Text #9

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4185. Min Act: -0.1700

Data Index: 1557393 (Python Code)

Max Activating Token Index: 566

Text #10

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4472. Min Act: -0.1700

Data Index: 1636794 (Python Code)

Max Activating Token Index: 194

Text #11

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4160. Min Act: -0.1700

Data Index: 684891 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4099. Min Act: -0.1700

Data Index: 1575132 (Python Code)

Max Activating Token Index: 264

Text #13

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.3915. Min Act: -0.1700

Data Index: 1561432 (Python Code)

Max Activating Token Index: 764

Text #14

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4017. Min Act: -0.1700

Data Index: 1560693 (Python Code)

Max Activating Token Index: 435

Text #15

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4009. Min Act: -0.1700

Data Index: 1612743 (Python Code)

Max Activating Token Index: 346

Text #16

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.3953. Min Act: -0.1700

Data Index: 1639852 (Python Code)

Max Activating Token Index: 698

Text #17

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.3861. Min Act: -0.1700

Data Index: 1561119 (Python Code)

Max Activating Token Index: 131

Text #18

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.3982. Min Act: -0.1700

Data Index: 1566501 (Python Code)

Max Activating Token Index: 612

Text #19

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.3780. Min Act: -0.1700

Data Index: 1540674 (Python Code)

Max Activating Token Index: 465