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

Dataset: Open Web Text

Neuron 1755 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: 3.8829. Min Range: -3.8829

Max Act: 3.8829. Min Act: -0.1700

Data Index: 5919903 (Open Web Text)

Max Activating Token Index: 196

Text #1

Max Range: 3.8829. Min Range: -3.8829

Max Act: 3.7737. Min Act: -0.1700

Data Index: 7545252 (Open Web Text)

Max Activating Token Index: 269

Text #2

Max Range: 3.8829. Min Range: -3.8829

Max Act: 3.7132. Min Act: -0.1700

Data Index: 5746360 (Open Web Text)

Max Activating Token Index: 851

Text #3

Max Range: 3.8829. Min Range: -3.8829

Max Act: 3.6826. Min Act: -0.1700

Data Index: 4558358 (Open Web Text)

Max Activating Token Index: 101

Text #4

Max Range: 3.8829. Min Range: -3.8829

Max Act: 3.6685. Min Act: -0.1700

Data Index: 8415182 (Open Web Text)

Max Activating Token Index: 233

Text #5

Max Range: 3.8829. Min Range: -3.8829

Max Act: 3.6726. Min Act: -0.1700

Data Index: 5394520 (Open Web Text)

Max Activating Token Index: 143

Text #6

Max Range: 3.8829. Min Range: -3.8829

Max Act: 3.6655. Min Act: -0.1700

Data Index: 1645435 (Open Web Text)

Max Activating Token Index: 686

Text #7

Max Range: 3.8829. Min Range: -3.8829

Max Act: 3.6118. Min Act: -0.1700

Data Index: 3784490 (Open Web Text)

Max Activating Token Index: 497

Text #8

Max Range: 3.8829. Min Range: -3.8829

Max Act: 3.5935. Min Act: -0.1700

Data Index: 4854395 (Open Web Text)

Max Activating Token Index: 984

Text #9

Max Range: 3.8829. Min Range: -3.8829

Max Act: 3.6116. Min Act: -0.1700

Data Index: 8054110 (Open Web Text)

Max Activating Token Index: 512

Text #10

Max Range: 3.8829. Min Range: -3.8829

Max Act: 3.6190. Min Act: -0.1700

Data Index: 7241563 (Open Web Text)

Max Activating Token Index: 567

Text #11

Max Range: 3.8829. Min Range: -3.8829

Max Act: 3.5918. Min Act: -0.1700

Data Index: 1643632 (Open Web Text)

Max Activating Token Index: 448

Text #12

Max Range: 3.8829. Min Range: -3.8829

Max Act: 3.6137. Min Act: -0.1700

Data Index: 458041 (Open Web Text)

Max Activating Token Index: 898

Text #13

Max Range: 3.8829. Min Range: -3.8829

Max Act: 3.6030. Min Act: -0.1700

Data Index: 6350874 (Open Web Text)

Max Activating Token Index: 560

Text #14

Max Range: 3.8829. Min Range: -3.8829

Max Act: 3.5531. Min Act: -0.1700

Data Index: 2127745 (Open Web Text)

Max Activating Token Index: 207

Text #15

Max Range: 3.8829. Min Range: -3.8829

Max Act: 3.5612. Min Act: -0.1700

Data Index: 6648124 (Open Web Text)

Max Activating Token Index: 327

Text #16

Max Range: 3.8829. Min Range: -3.8829

Max Act: 3.5584. Min Act: -0.1700

Data Index: 7760142 (Open Web Text)

Max Activating Token Index: 917

Text #17

Max Range: 3.8829. Min Range: -3.8829

Max Act: 3.5853. Min Act: -0.1700

Data Index: 1643886 (Open Web Text)

Max Activating Token Index: 31

Text #18

Max Range: 3.8829. Min Range: -3.8829

Max Act: 3.5703. Min Act: -0.1700

Data Index: 7022340 (Open Web Text)

Max Activating Token Index: 286

Text #19

Max Range: 3.8829. Min Range: -3.8829

Max Act: 3.5410. Min Act: -0.1700

Data Index: 921642 (Open Web Text)

Max Activating Token Index: 866