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

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

Neuron 1294 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0382. Min Range: -5.0382

Max Act: 5.0382. Min Act: -0.1700

Data Index: 1031348 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 5.0382. Min Range: -5.0382

Max Act: 5.0069. Min Act: -0.1700

Data Index: 493389 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.9757. Min Act: -0.1700

Data Index: 1090211 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.9444. Min Act: -0.1700

Data Index: 414119 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.9444. Min Act: -0.1700

Data Index: 873541 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.8819. Min Act: -0.1700

Data Index: 92404 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.9132. Min Act: -0.1700

Data Index: 1238992 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.8819. Min Act: -0.1700

Data Index: 898121 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.8819. Min Act: -0.1700

Data Index: 210866 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.8194. Min Act: -0.1700

Data Index: 480249 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.8194. Min Act: -0.1700

Data Index: 217432 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.8507. Min Act: -0.1700

Data Index: 430808 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.8507. Min Act: -0.1700

Data Index: 71978 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.8507. Min Act: -0.1700

Data Index: 114542 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.8194. Min Act: -0.1700

Data Index: 664430 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.8194. Min Act: -0.1700

Data Index: 1216126 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.7569. Min Act: -0.1700

Data Index: 1075988 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.7882. Min Act: -0.1700

Data Index: 811134 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.8194. Min Act: -0.1700

Data Index: 1124216 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.7569. Min Act: -0.1700

Data Index: 836000 (C4 (Web Text))

Max Activating Token Index: 425