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

Dataset: Open Web Text

Neuron 2749 in Layer 6

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: 3.9639. Min Range: -3.9639

Max Act: 3.9639. Min Act: -0.1700

Data Index: 5022391 (Open Web Text)

Max Activating Token Index: 1003

Text #1

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.9022. Min Act: -0.1700

Data Index: 4567478 (Open Web Text)

Max Activating Token Index: 543

Text #2

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.8826. Min Act: -0.1700

Data Index: 7001053 (Open Web Text)

Max Activating Token Index: 186

Text #3

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.8431. Min Act: -0.1700

Data Index: 6618103 (Open Web Text)

Max Activating Token Index: 481

Text #4

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.8874. Min Act: -0.1700

Data Index: 7230000 (Open Web Text)

Max Activating Token Index: 356

Text #5

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.8140. Min Act: -0.1700

Data Index: 5494313 (Open Web Text)

Max Activating Token Index: 769

Text #6

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.8531. Min Act: -0.1700

Data Index: 2746685 (Open Web Text)

Max Activating Token Index: 395

Text #7

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.8052. Min Act: -0.1700

Data Index: 2381514 (Open Web Text)

Max Activating Token Index: 698

Text #8

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7742. Min Act: -0.1700

Data Index: 2114154 (Open Web Text)

Max Activating Token Index: 954

Text #9

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7770. Min Act: -0.1700

Data Index: 7483991 (Open Web Text)

Max Activating Token Index: 460

Text #10

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7899. Min Act: -0.1700

Data Index: 2078720 (Open Web Text)

Max Activating Token Index: 497

Text #11

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7415. Min Act: -0.1700

Data Index: 7526373 (Open Web Text)

Max Activating Token Index: 518

Text #12

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7355. Min Act: -0.1700

Data Index: 835466 (Open Web Text)

Max Activating Token Index: 167

Text #13

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7259. Min Act: -0.1700

Data Index: 5074514 (Open Web Text)

Max Activating Token Index: 647

Text #14

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7341. Min Act: -0.1700

Data Index: 2723451 (Open Web Text)

Max Activating Token Index: 433

Text #15

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7124. Min Act: -0.1700

Data Index: 5821285 (Open Web Text)

Max Activating Token Index: 746

Text #16

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7046. Min Act: -0.1700

Data Index: 6893219 (Open Web Text)

Max Activating Token Index: 848

Text #17

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.6628. Min Act: -0.1700

Data Index: 8630426 (Open Web Text)

Max Activating Token Index: 951

Text #18

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.6665. Min Act: -0.1700

Data Index: 4973052 (Open Web Text)

Max Activating Token Index: 962

Text #19

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.6650. Min Act: -0.1700

Data Index: 1742091 (Open Web Text)

Max Activating Token Index: 417