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

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

Neuron 1237 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.7893. Min Act: -0.1700

Data Index: 304229 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.6641. Min Act: -0.1700

Data Index: 1227600 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.6015. Min Act: -0.1700

Data Index: 453357 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.5702. Min Act: -0.1700

Data Index: 7266 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.5702. Min Act: -0.1700

Data Index: 130058 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.5075. Min Act: -0.1700

Data Index: 53997 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.5702. Min Act: -0.1700

Data Index: 536533 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.5389. Min Act: -0.1700

Data Index: 1134210 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.5389. Min Act: -0.1700

Data Index: 447844 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.4762. Min Act: -0.1700

Data Index: 1030826 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.4762. Min Act: -0.1700

Data Index: 195205 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.4449. Min Act: -0.1700

Data Index: 753280 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.4135. Min Act: -0.1700

Data Index: 196697 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.4449. Min Act: -0.1700

Data Index: 116308 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.3821. Min Act: -0.1700

Data Index: 380234 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.4135. Min Act: -0.1700

Data Index: 1338082 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.4135. Min Act: -0.1700

Data Index: 1213836 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.3821. Min Act: -0.1700

Data Index: 487720 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.4449. Min Act: -0.1700

Data Index: 1127238 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.4135. Min Act: -0.1700

Data Index: 883403 (C4 (Web Text))

Max Activating Token Index: 919