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

Dataset: Open Web Text

Neuron 2048 in Layer 2

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: 3.8040. Min Range: -3.8040

Max Act: 3.7928. Min Act: -0.1700

Data Index: 7437423 (Open Web Text)

Max Activating Token Index: 184

Text #1

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.8040. Min Act: -0.1700

Data Index: 6031399 (Open Web Text)

Max Activating Token Index: 526

Text #2

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.8031. Min Act: -0.1700

Data Index: 5405155 (Open Web Text)

Max Activating Token Index: 392

Text #3

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.7816. Min Act: -0.1700

Data Index: 3125534 (Open Web Text)

Max Activating Token Index: 884

Text #4

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.7697. Min Act: -0.1700

Data Index: 7908853 (Open Web Text)

Max Activating Token Index: 596

Text #5

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.7248. Min Act: -0.1700

Data Index: 6762859 (Open Web Text)

Max Activating Token Index: 546

Text #6

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.6957. Min Act: -0.1700

Data Index: 5739752 (Open Web Text)

Max Activating Token Index: 869

Text #7

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.6824. Min Act: -0.1700

Data Index: 7974246 (Open Web Text)

Max Activating Token Index: 82

Text #8

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.7278. Min Act: -0.1700

Data Index: 1330268 (Open Web Text)

Max Activating Token Index: 688

Text #9

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.7246. Min Act: -0.1700

Data Index: 982836 (Open Web Text)

Max Activating Token Index: 1019

Text #10

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.6976. Min Act: -0.1700

Data Index: 8481458 (Open Web Text)

Max Activating Token Index: 275

Text #11

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.7099. Min Act: -0.1700

Data Index: 58278 (Open Web Text)

Max Activating Token Index: 483

Text #12

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.7033. Min Act: -0.1700

Data Index: 6225712 (Open Web Text)

Max Activating Token Index: 629

Text #13

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.7023. Min Act: -0.1700

Data Index: 1510734 (Open Web Text)

Max Activating Token Index: 480

Text #14

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.6583. Min Act: -0.1700

Data Index: 5830979 (Open Web Text)

Max Activating Token Index: 576

Text #15

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.6692. Min Act: -0.1700

Data Index: 7777399 (Open Web Text)

Max Activating Token Index: 771

Text #16

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.7044. Min Act: -0.1700

Data Index: 7417890 (Open Web Text)

Max Activating Token Index: 845

Text #17

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.6733. Min Act: -0.1700

Data Index: 3812267 (Open Web Text)

Max Activating Token Index: 1002

Text #18

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.6340. Min Act: -0.1700

Data Index: 7083648 (Open Web Text)

Max Activating Token Index: 202

Text #19

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.6451. Min Act: -0.1700

Data Index: 741319 (Open Web Text)

Max Activating Token Index: 722