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

Dataset: Open Web Text

Neuron 2348 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: 4.6994. Min Range: -4.6994

Max Act: 4.6994. Min Act: -0.1700

Data Index: 2764356 (Open Web Text)

Max Activating Token Index: 547

Text #1

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.6165. Min Act: -0.1700

Data Index: 4413748 (Open Web Text)

Max Activating Token Index: 815

Text #2

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4971. Min Act: -0.1700

Data Index: 4718732 (Open Web Text)

Max Activating Token Index: 620

Text #3

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4904. Min Act: -0.1700

Data Index: 1433751 (Open Web Text)

Max Activating Token Index: 477

Text #4

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4664. Min Act: -0.1700

Data Index: 6357707 (Open Web Text)

Max Activating Token Index: 364

Text #5

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4575. Min Act: -0.1700

Data Index: 5719985 (Open Web Text)

Max Activating Token Index: 457

Text #6

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4373. Min Act: -0.1700

Data Index: 5569265 (Open Web Text)

Max Activating Token Index: 476

Text #7

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4919. Min Act: -0.1700

Data Index: 2785476 (Open Web Text)

Max Activating Token Index: 643

Text #8

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4080. Min Act: -0.1700

Data Index: 6258621 (Open Web Text)

Max Activating Token Index: 348

Text #9

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4314. Min Act: -0.1700

Data Index: 4188608 (Open Web Text)

Max Activating Token Index: 72

Text #10

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4145. Min Act: -0.1700

Data Index: 7535628 (Open Web Text)

Max Activating Token Index: 802

Text #11

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4330. Min Act: -0.1700

Data Index: 1138566 (Open Web Text)

Max Activating Token Index: 574

Text #12

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4022. Min Act: -0.1700

Data Index: 8268696 (Open Web Text)

Max Activating Token Index: 520

Text #13

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4146. Min Act: -0.1700

Data Index: 5123299 (Open Web Text)

Max Activating Token Index: 864

Text #14

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4007. Min Act: -0.1700

Data Index: 2241620 (Open Web Text)

Max Activating Token Index: 112

Text #15

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.4098. Min Act: -0.1700

Data Index: 2026963 (Open Web Text)

Max Activating Token Index: 793

Text #16

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.3673. Min Act: -0.1700

Data Index: 6537737 (Open Web Text)

Max Activating Token Index: 940

Text #17

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.3995. Min Act: -0.1700

Data Index: 4287359 (Open Web Text)

Max Activating Token Index: 657

Text #18

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.3706. Min Act: -0.1700

Data Index: 3606025 (Open Web Text)

Max Activating Token Index: 689

Text #19

Max Range: 4.6994. Min Range: -4.6994

Max Act: 4.3582. Min Act: -0.1700

Data Index: 5289691 (Open Web Text)

Max Activating Token Index: 349