Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 223 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.0225. Min Range: -3.0225

Max Act: 3.0225. Min Act: -0.1700

Data Index: 879462 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 3.0225. Min Range: -3.0225

Max Act: 3.0225. Min Act: -0.1700

Data Index: 886641 (C4 (Web Text))

Max Activating Token Index: 1

Text #2

Max Range: 3.0225. Min Range: -3.0225

Max Act: 3.0225. Min Act: -0.1700

Data Index: 91445 (C4 (Web Text))

Max Activating Token Index: 1

Text #3

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.9751. Min Act: -0.1700

Data Index: 267 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.9276. Min Act: -0.1700

Data Index: 1490424 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.9276. Min Act: -0.1700

Data Index: 371026 (C4 (Web Text))

Max Activating Token Index: 1

Text #6

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.9276. Min Act: -0.1700

Data Index: 1220480 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.9276. Min Act: -0.1700

Data Index: 1237001 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.9276. Min Act: -0.1700

Data Index: 1263547 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.9276. Min Act: -0.1700

Data Index: 1311393 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.9276. Min Act: -0.1700

Data Index: 182279 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.9276. Min Act: -0.1700

Data Index: 282513 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.9276. Min Act: -0.1700

Data Index: 492572 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.9276. Min Act: -0.1700

Data Index: 208701 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.9276. Min Act: -0.1700

Data Index: 471663 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.9276. Min Act: -0.1700

Data Index: 867390 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.8642. Min Act: -0.1700

Data Index: 99833 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.8642. Min Act: -0.1700

Data Index: 1401817 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.8483. Min Act: -0.1700

Data Index: 209411 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.8642. Min Act: -0.1700

Data Index: 349165 (C4 (Web Text))

Max Activating Token Index: 1