Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1894 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.8001. Min Act: -0.1700

Data Index: 698561 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.8313. Min Act: -0.1700

Data Index: 1312346 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.8001. Min Act: -0.1700

Data Index: 282208 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.7375. Min Act: -0.1700

Data Index: 964077 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.7062. Min Act: -0.1700

Data Index: 738977 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6749. Min Act: -0.1700

Data Index: 189435 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6749. Min Act: -0.1700

Data Index: 1220969 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6749. Min Act: -0.1700

Data Index: 249978 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6436. Min Act: -0.1700

Data Index: 38490 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6123. Min Act: -0.1700

Data Index: 1078638 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6436. Min Act: -0.1700

Data Index: 970226 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6123. Min Act: -0.1700

Data Index: 436726 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.6123. Min Act: -0.1700

Data Index: 1043252 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.5810. Min Act: -0.1700

Data Index: 184354 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.5810. Min Act: -0.1679

Data Index: 1065224 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.5810. Min Act: -0.1700

Data Index: 400413 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.5810. Min Act: -0.1700

Data Index: 175037 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.5497. Min Act: -0.1700

Data Index: 611361 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.5810. Min Act: -0.1700

Data Index: 644731 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 3.8313. Min Range: -3.8313

Max Act: 3.5810. Min Act: -0.1700

Data Index: 795984 (C4 (Web Text))

Max Activating Token Index: 540