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

Dataset: Open Web Text

Neuron 57 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: 1.5786. Min Range: -1.5786

Max Act: 1.5786. Min Act: -0.1700

Data Index: 2243831 (Open Web Text)

Max Activating Token Index: 899

Text #1

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.5406. Min Act: -0.1700

Data Index: 6892438 (Open Web Text)

Max Activating Token Index: 900

Text #2

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.5345. Min Act: -0.1700

Data Index: 6689434 (Open Web Text)

Max Activating Token Index: 399

Text #3

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.5168. Min Act: -0.1695

Data Index: 1485592 (Open Web Text)

Max Activating Token Index: 676

Text #4

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.5149. Min Act: -0.1700

Data Index: 320892 (Open Web Text)

Max Activating Token Index: 813

Text #5

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.5099. Min Act: -0.1700

Data Index: 1931471 (Open Web Text)

Max Activating Token Index: 528

Text #6

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.5075. Min Act: -0.1700

Data Index: 3915096 (Open Web Text)

Max Activating Token Index: 946

Text #7

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.5162. Min Act: -0.1700

Data Index: 8451577 (Open Web Text)

Max Activating Token Index: 215

Text #8

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.5004. Min Act: -0.1700

Data Index: 1693038 (Open Web Text)

Max Activating Token Index: 274

Text #9

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.4974. Min Act: -0.1700

Data Index: 856288 (Open Web Text)

Max Activating Token Index: 859

Text #10

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.5151. Min Act: -0.1700

Data Index: 2355185 (Open Web Text)

Max Activating Token Index: 309

Text #11

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.5153. Min Act: -0.1696

Data Index: 7548447 (Open Web Text)

Max Activating Token Index: 839

Text #12

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.5099. Min Act: -0.1700

Data Index: 3614871 (Open Web Text)

Max Activating Token Index: 385

Text #13

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.5020. Min Act: -0.1700

Data Index: 8083583 (Open Web Text)

Max Activating Token Index: 333

Text #14

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.4927. Min Act: -0.1700

Data Index: 5746825 (Open Web Text)

Max Activating Token Index: 515

Text #15

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.5042. Min Act: -0.1700

Data Index: 2956094 (Open Web Text)

Max Activating Token Index: 266

Text #16

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.4959. Min Act: -0.1700

Data Index: 4765152 (Open Web Text)

Max Activating Token Index: 322

Text #17

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.4964. Min Act: -0.1700

Data Index: 8072959 (Open Web Text)

Max Activating Token Index: 970

Text #18

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.4885. Min Act: -0.1700

Data Index: 7743503 (Open Web Text)

Max Activating Token Index: 987

Text #19

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.4938. Min Act: -0.1700

Data Index: 6068601 (Open Web Text)

Max Activating Token Index: 333