Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 342 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.0882. Min Range: -4.0882

Max Act: 4.0882. Min Act: -0.1700

Data Index: 6280014 (Open Web Text)

Max Activating Token Index: 276

Text #1

Max Range: 4.0882. Min Range: -4.0882

Max Act: 4.0516. Min Act: -0.1700

Data Index: 8770809 (Open Web Text)

Max Activating Token Index: 766

Text #2

Max Range: 4.0882. Min Range: -4.0882

Max Act: 4.0370. Min Act: -0.1700

Data Index: 5444076 (Open Web Text)

Max Activating Token Index: 138

Text #3

Max Range: 4.0882. Min Range: -4.0882

Max Act: 4.0334. Min Act: -0.1700

Data Index: 3318674 (Open Web Text)

Max Activating Token Index: 68

Text #4

Max Range: 4.0882. Min Range: -4.0882

Max Act: 4.0292. Min Act: -0.1700

Data Index: 6096334 (Open Web Text)

Max Activating Token Index: 617

Text #5

Max Range: 4.0882. Min Range: -4.0882

Max Act: 4.0099. Min Act: -0.1700

Data Index: 5486972 (Open Web Text)

Max Activating Token Index: 526

Text #6

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9844. Min Act: -0.1700

Data Index: 5374085 (Open Web Text)

Max Activating Token Index: 310

Text #7

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9690. Min Act: -0.1700

Data Index: 5818371 (Open Web Text)

Max Activating Token Index: 831

Text #8

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9824. Min Act: -0.1700

Data Index: 2964566 (Open Web Text)

Max Activating Token Index: 422

Text #9

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9542. Min Act: -0.1700

Data Index: 1226349 (Open Web Text)

Max Activating Token Index: 525

Text #10

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9118. Min Act: -0.1700

Data Index: 1181368 (Open Web Text)

Max Activating Token Index: 68

Text #11

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9211. Min Act: -0.1700

Data Index: 5931961 (Open Web Text)

Max Activating Token Index: 197

Text #12

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9298. Min Act: -0.1700

Data Index: 1567258 (Open Web Text)

Max Activating Token Index: 959

Text #13

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9148. Min Act: -0.1700

Data Index: 7030673 (Open Web Text)

Max Activating Token Index: 931

Text #14

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9115. Min Act: -0.1700

Data Index: 2305311 (Open Web Text)

Max Activating Token Index: 927

Text #15

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9448. Min Act: -0.1700

Data Index: 4721028 (Open Web Text)

Max Activating Token Index: 888

Text #16

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9078. Min Act: -0.1700

Data Index: 4295797 (Open Web Text)

Max Activating Token Index: 735

Text #17

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9381. Min Act: -0.1700

Data Index: 4221573 (Open Web Text)

Max Activating Token Index: 148

Text #18

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.8930. Min Act: -0.1700

Data Index: 6262088 (Open Web Text)

Max Activating Token Index: 671

Text #19

Max Range: 4.0882. Min Range: -4.0882

Max Act: 3.9002. Min Act: -0.1700

Data Index: 6752139 (Open Web Text)

Max Activating Token Index: 253