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

Dataset: Open Web Text

Neuron 1006 in Layer 4

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: 3.8973. Min Range: -3.8973

Max Act: 3.8973. Min Act: -0.1700

Data Index: 7530243 (Open Web Text)

Max Activating Token Index: 338

Text #1

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.8448. Min Act: -0.1700

Data Index: 7004202 (Open Web Text)

Max Activating Token Index: 195

Text #2

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.8346. Min Act: -0.1700

Data Index: 486323 (Open Web Text)

Max Activating Token Index: 944

Text #3

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.8102. Min Act: -0.1700

Data Index: 7224121 (Open Web Text)

Max Activating Token Index: 888

Text #4

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.8653. Min Act: -0.1700

Data Index: 7166618 (Open Web Text)

Max Activating Token Index: 565

Text #5

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.8330. Min Act: -0.1700

Data Index: 8414143 (Open Web Text)

Max Activating Token Index: 972

Text #6

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.8197. Min Act: -0.1700

Data Index: 2129086 (Open Web Text)

Max Activating Token Index: 130

Text #7

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.8150. Min Act: -0.1700

Data Index: 4813893 (Open Web Text)

Max Activating Token Index: 229

Text #8

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7911. Min Act: -0.1700

Data Index: 4142124 (Open Web Text)

Max Activating Token Index: 190

Text #9

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.8050. Min Act: -0.1700

Data Index: 7957589 (Open Web Text)

Max Activating Token Index: 281

Text #10

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7730. Min Act: -0.1700

Data Index: 1072748 (Open Web Text)

Max Activating Token Index: 568

Text #11

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7810. Min Act: -0.1700

Data Index: 8330309 (Open Web Text)

Max Activating Token Index: 237

Text #12

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7863. Min Act: -0.1700

Data Index: 7126919 (Open Web Text)

Max Activating Token Index: 335

Text #13

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7715. Min Act: -0.1700

Data Index: 6732489 (Open Web Text)

Max Activating Token Index: 569

Text #14

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7919. Min Act: -0.1700

Data Index: 6681084 (Open Web Text)

Max Activating Token Index: 464

Text #15

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7368. Min Act: -0.1700

Data Index: 1681693 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7321. Min Act: -0.1700

Data Index: 1151087 (Open Web Text)

Max Activating Token Index: 834

Text #17

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7385. Min Act: -0.1700

Data Index: 2777581 (Open Web Text)

Max Activating Token Index: 853

Text #18

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7229. Min Act: -0.1700

Data Index: 5027343 (Open Web Text)

Max Activating Token Index: 292

Text #19

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7315. Min Act: -0.1700

Data Index: 905528 (Open Web Text)

Max Activating Token Index: 16