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

Dataset: Open Web Text

Neuron 2129 in Layer 3

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: 3.9466. Min Range: -3.9466

Max Act: 3.9456. Min Act: -0.1700

Data Index: 5096103 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 3.9466. Min Range: -3.9466

Max Act: 3.9466. Min Act: -0.1700

Data Index: 6789225 (Open Web Text)

Max Activating Token Index: 147

Text #2

Max Range: 3.9466. Min Range: -3.9466

Max Act: 3.8807. Min Act: -0.1700

Data Index: 8031413 (Open Web Text)

Max Activating Token Index: 789

Text #3

Max Range: 3.9466. Min Range: -3.9466

Max Act: 3.9099. Min Act: -0.1700

Data Index: 1255101 (Open Web Text)

Max Activating Token Index: 682

Text #4

Max Range: 3.9466. Min Range: -3.9466

Max Act: 3.9083. Min Act: -0.1700

Data Index: 5690405 (Open Web Text)

Max Activating Token Index: 275

Text #5

Max Range: 3.9466. Min Range: -3.9466

Max Act: 3.9044. Min Act: -0.1700

Data Index: 4927201 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.9466. Min Range: -3.9466

Max Act: 3.8889. Min Act: -0.1700

Data Index: 6805803 (Open Web Text)

Max Activating Token Index: 934

Text #7

Max Range: 3.9466. Min Range: -3.9466

Max Act: 3.8898. Min Act: -0.1700

Data Index: 6143286 (Open Web Text)

Max Activating Token Index: 820

Text #8

Max Range: 3.9466. Min Range: -3.9466

Max Act: 3.8773. Min Act: -0.1700

Data Index: 3115957 (Open Web Text)

Max Activating Token Index: 64

Text #9

Max Range: 3.9466. Min Range: -3.9466

Max Act: 3.9251. Min Act: -0.1700

Data Index: 4022009 (Open Web Text)

Max Activating Token Index: 493

Text #10

Max Range: 3.9466. Min Range: -3.9466

Max Act: 3.8752. Min Act: -0.1700

Data Index: 7356538 (Open Web Text)

Max Activating Token Index: 55

Text #11

Max Range: 3.9466. Min Range: -3.9466

Max Act: 3.8231. Min Act: -0.1700

Data Index: 6653768 (Open Web Text)

Max Activating Token Index: 225

Text #12

Max Range: 3.9466. Min Range: -3.9466

Max Act: 3.8301. Min Act: -0.1700

Data Index: 1968159 (Open Web Text)

Max Activating Token Index: 732

Text #13

Max Range: 3.9466. Min Range: -3.9466

Max Act: 3.8650. Min Act: -0.1700

Data Index: 6904270 (Open Web Text)

Max Activating Token Index: 486

Text #14

Max Range: 3.9466. Min Range: -3.9466

Max Act: 3.8633. Min Act: -0.1700

Data Index: 2308667 (Open Web Text)

Max Activating Token Index: 901

Text #15

Max Range: 3.9466. Min Range: -3.9466

Max Act: 3.7786. Min Act: -0.1700

Data Index: 949645 (Open Web Text)

Max Activating Token Index: 25

Text #16

Max Range: 3.9466. Min Range: -3.9466

Max Act: 3.7973. Min Act: -0.1700

Data Index: 3115954 (Open Web Text)

Max Activating Token Index: 277

Text #17

Max Range: 3.9466. Min Range: -3.9466

Max Act: 3.8466. Min Act: -0.1700

Data Index: 2690260 (Open Web Text)

Max Activating Token Index: 951

Text #18

Max Range: 3.9466. Min Range: -3.9466

Max Act: 3.7954. Min Act: -0.1700

Data Index: 4474901 (Open Web Text)

Max Activating Token Index: 255

Text #19

Max Range: 3.9466. Min Range: -3.9466

Max Act: 3.8219. Min Act: -0.1700

Data Index: 218311 (Open Web Text)

Max Activating Token Index: 734