Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1324 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.0524. Min Range: -3.0524

Max Act: 3.0524. Min Act: -0.1700

Data Index: 425705 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 3.0524. Min Range: -3.0524

Max Act: 3.0208. Min Act: -0.1700

Data Index: 1208396 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 3.0524. Min Range: -3.0524

Max Act: 3.0208. Min Act: -0.1700

Data Index: 326394 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 3.0524. Min Range: -3.0524

Max Act: 3.0208. Min Act: -0.1700

Data Index: 1265015 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 3.0524. Min Range: -3.0524

Max Act: 3.0366. Min Act: -0.1700

Data Index: 106546 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.9734. Min Act: -0.1700

Data Index: 1323212 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.9734. Min Act: -0.1700

Data Index: 855978 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.9575. Min Act: -0.1700

Data Index: 1075769 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.9734. Min Act: -0.1700

Data Index: 166681 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.9417. Min Act: -0.1700

Data Index: 850099 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.9417. Min Act: -0.1700

Data Index: 470237 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.9259. Min Act: -0.1700

Data Index: 225452 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.9259. Min Act: -0.1700

Data Index: 910981 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.9417. Min Act: -0.1700

Data Index: 1106321 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.9100. Min Act: -0.1700

Data Index: 1320273 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.9100. Min Act: -0.1700

Data Index: 400290 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.8942. Min Act: -0.1700

Data Index: 1240819 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.9259. Min Act: -0.1700

Data Index: 26518 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.8942. Min Act: -0.1700

Data Index: 1280126 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 3.0524. Min Range: -3.0524

Max Act: 2.8783. Min Act: -0.1700

Data Index: 291451 (C4 (Web Text))

Max Activating Token Index: 550