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

Dataset: Open Web Text

Neuron 367 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: 6.2513. Min Range: -6.2513

Max Act: 6.2513. Min Act: -0.1700

Data Index: 4338136 (Open Web Text)

Max Activating Token Index: 151

Text #1

Max Range: 6.2513. Min Range: -6.2513

Max Act: 6.2393. Min Act: -0.1700

Data Index: 1200171 (Open Web Text)

Max Activating Token Index: 206

Text #2

Max Range: 6.2513. Min Range: -6.2513

Max Act: 6.1880. Min Act: -0.1700

Data Index: 3000329 (Open Web Text)

Max Activating Token Index: 33

Text #3

Max Range: 6.2513. Min Range: -6.2513

Max Act: 6.1503. Min Act: -0.1700

Data Index: 7036387 (Open Web Text)

Max Activating Token Index: 39

Text #4

Max Range: 6.2513. Min Range: -6.2513

Max Act: 6.0882. Min Act: -0.1700

Data Index: 540304 (Open Web Text)

Max Activating Token Index: 87

Text #5

Max Range: 6.2513. Min Range: -6.2513

Max Act: 6.0592. Min Act: -0.1700

Data Index: 4474493 (Open Web Text)

Max Activating Token Index: 16

Text #6

Max Range: 6.2513. Min Range: -6.2513

Max Act: 6.0472. Min Act: -0.1700

Data Index: 3297451 (Open Web Text)

Max Activating Token Index: 203

Text #7

Max Range: 6.2513. Min Range: -6.2513

Max Act: 6.0738. Min Act: -0.1700

Data Index: 2962696 (Open Web Text)

Max Activating Token Index: 195

Text #8

Max Range: 6.2513. Min Range: -6.2513

Max Act: 6.0290. Min Act: -0.1700

Data Index: 6752397 (Open Web Text)

Max Activating Token Index: 519

Text #9

Max Range: 6.2513. Min Range: -6.2513

Max Act: 5.9726. Min Act: -0.1700

Data Index: 5391427 (Open Web Text)

Max Activating Token Index: 545

Text #10

Max Range: 6.2513. Min Range: -6.2513

Max Act: 5.9742. Min Act: -0.1700

Data Index: 7794354 (Open Web Text)

Max Activating Token Index: 21

Text #11

Max Range: 6.2513. Min Range: -6.2513

Max Act: 5.9783. Min Act: -0.1700

Data Index: 361591 (Open Web Text)

Max Activating Token Index: 79

Text #12

Max Range: 6.2513. Min Range: -6.2513

Max Act: 5.9200. Min Act: -0.1700

Data Index: 4560859 (Open Web Text)

Max Activating Token Index: 183

Text #13

Max Range: 6.2513. Min Range: -6.2513

Max Act: 5.9470. Min Act: -0.1700

Data Index: 7713188 (Open Web Text)

Max Activating Token Index: 28

Text #14

Max Range: 6.2513. Min Range: -6.2513

Max Act: 5.8987. Min Act: -0.1700

Data Index: 4437832 (Open Web Text)

Max Activating Token Index: 229

Text #15

Max Range: 6.2513. Min Range: -6.2513

Max Act: 5.8802. Min Act: -0.1700

Data Index: 4351880 (Open Web Text)

Max Activating Token Index: 79

Text #16

Max Range: 6.2513. Min Range: -6.2513

Max Act: 5.8602. Min Act: -0.1700

Data Index: 4982975 (Open Web Text)

Max Activating Token Index: 477

Text #17

Max Range: 6.2513. Min Range: -6.2513

Max Act: 5.8495. Min Act: -0.1700

Data Index: 1690715 (Open Web Text)

Max Activating Token Index: 249

Text #18

Max Range: 6.2513. Min Range: -6.2513

Max Act: 5.8314. Min Act: -0.1700

Data Index: 795547 (Open Web Text)

Max Activating Token Index: 234

Text #19

Max Range: 6.2513. Min Range: -6.2513

Max Act: 5.8213. Min Act: -0.1700

Data Index: 3536937 (Open Web Text)

Max Activating Token Index: 186