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

Dataset: Open Web Text

Neuron 2574 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: 5.9215. Min Range: -5.9215

Max Act: 5.9149. Min Act: -0.1700

Data Index: 1482964 (Open Web Text)

Max Activating Token Index: 613

Text #1

Max Range: 5.9215. Min Range: -5.9215

Max Act: 5.8765. Min Act: -0.1700

Data Index: 2162936 (Open Web Text)

Max Activating Token Index: 562

Text #2

Max Range: 5.9215. Min Range: -5.9215

Max Act: 5.9215. Min Act: -0.1700

Data Index: 5789088 (Open Web Text)

Max Activating Token Index: 73

Text #3

Max Range: 5.9215. Min Range: -5.9215

Max Act: 5.8885. Min Act: -0.1700

Data Index: 3297965 (Open Web Text)

Max Activating Token Index: 151

Text #4

Max Range: 5.9215. Min Range: -5.9215

Max Act: 5.8779. Min Act: -0.1700

Data Index: 4996318 (Open Web Text)

Max Activating Token Index: 380

Text #5

Max Range: 5.9215. Min Range: -5.9215

Max Act: 5.8845. Min Act: -0.1700

Data Index: 3052859 (Open Web Text)

Max Activating Token Index: 162

Text #6

Max Range: 5.9215. Min Range: -5.9215

Max Act: 5.8886. Min Act: -0.1700

Data Index: 5741990 (Open Web Text)

Max Activating Token Index: 517

Text #7

Max Range: 5.9215. Min Range: -5.9215

Max Act: 5.8665. Min Act: -0.1700

Data Index: 1914677 (Open Web Text)

Max Activating Token Index: 276

Text #8

Max Range: 5.9215. Min Range: -5.9215

Max Act: 5.8141. Min Act: -0.1700

Data Index: 8689010 (Open Web Text)

Max Activating Token Index: 529

Text #9

Max Range: 5.9215. Min Range: -5.9215

Max Act: 5.8044. Min Act: -0.1700

Data Index: 4511050 (Open Web Text)

Max Activating Token Index: 719

Text #10

Max Range: 5.9215. Min Range: -5.9215

Max Act: 5.8098. Min Act: -0.1700

Data Index: 3481814 (Open Web Text)

Max Activating Token Index: 41

Text #11

Max Range: 5.9215. Min Range: -5.9215

Max Act: 5.8137. Min Act: -0.1700

Data Index: 8573823 (Open Web Text)

Max Activating Token Index: 536

Text #12

Max Range: 5.9215. Min Range: -5.9215

Max Act: 5.8171. Min Act: -0.1700

Data Index: 8689239 (Open Web Text)

Max Activating Token Index: 618

Text #13

Max Range: 5.9215. Min Range: -5.9215

Max Act: 5.8077. Min Act: -0.1700

Data Index: 1873886 (Open Web Text)

Max Activating Token Index: 230

Text #14

Max Range: 5.9215. Min Range: -5.9215

Max Act: 5.7650. Min Act: -0.1700

Data Index: 2410801 (Open Web Text)

Max Activating Token Index: 560

Text #15

Max Range: 5.9215. Min Range: -5.9215

Max Act: 5.7873. Min Act: -0.1700

Data Index: 5643903 (Open Web Text)

Max Activating Token Index: 528

Text #16

Max Range: 5.9215. Min Range: -5.9215

Max Act: 5.7854. Min Act: -0.1700

Data Index: 7853584 (Open Web Text)

Max Activating Token Index: 64

Text #17

Max Range: 5.9215. Min Range: -5.9215

Max Act: 5.7976. Min Act: -0.1700

Data Index: 5422735 (Open Web Text)

Max Activating Token Index: 428

Text #18

Max Range: 5.9215. Min Range: -5.9215

Max Act: 5.8162. Min Act: -0.1700

Data Index: 2944147 (Open Web Text)

Max Activating Token Index: 876

Text #19

Max Range: 5.9215. Min Range: -5.9215

Max Act: 5.7865. Min Act: -0.1700

Data Index: 3946018 (Open Web Text)

Max Activating Token Index: 986