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

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

Neuron 369 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: 3.5378. Min Range: -3.5378

Max Act: 3.5378. Min Act: -0.1700

Data Index: 253741 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.4907. Min Act: -0.1700

Data Index: 1186414 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.4907. Min Act: -0.1700

Data Index: 669133 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.5064. Min Act: -0.1700

Data Index: 1347471 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.4751. Min Act: -0.1700

Data Index: 1163725 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.4280. Min Act: -0.1700

Data Index: 10862 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.4280. Min Act: -0.1700

Data Index: 424086 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.4437. Min Act: -0.1700

Data Index: 369347 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3967. Min Act: -0.1700

Data Index: 1171648 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3967. Min Act: -0.1700

Data Index: 1130725 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3967. Min Act: -0.1700

Data Index: 786532 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3967. Min Act: -0.1700

Data Index: 1019928 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3967. Min Act: -0.1700

Data Index: 670772 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3496. Min Act: -0.1700

Data Index: 1182792 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3496. Min Act: -0.1700

Data Index: 623871 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3496. Min Act: -0.1700

Data Index: 259064 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3182. Min Act: -0.1700

Data Index: 1175594 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3339. Min Act: -0.1700

Data Index: 88601 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3339. Min Act: -0.1700

Data Index: 1024218 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 3.5378. Min Range: -3.5378

Max Act: 3.3339. Min Act: -0.1700

Data Index: 113516 (C4 (Web Text))

Max Activating Token Index: 415