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

Dataset: Open Web Text

Neuron 1764 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: 3.7003. Min Range: -3.7003

Max Act: 3.7003. Min Act: -0.1700

Data Index: 1069102 (Open Web Text)

Max Activating Token Index: 380

Text #1

Max Range: 3.7003. Min Range: -3.7003

Max Act: 3.6701. Min Act: -0.1700

Data Index: 8726181 (Open Web Text)

Max Activating Token Index: 474

Text #2

Max Range: 3.7003. Min Range: -3.7003

Max Act: 3.6452. Min Act: -0.1700

Data Index: 7653770 (Open Web Text)

Max Activating Token Index: 524

Text #3

Max Range: 3.7003. Min Range: -3.7003

Max Act: 3.6503. Min Act: -0.1700

Data Index: 7082557 (Open Web Text)

Max Activating Token Index: 493

Text #4

Max Range: 3.7003. Min Range: -3.7003

Max Act: 3.6491. Min Act: -0.1700

Data Index: 4765423 (Open Web Text)

Max Activating Token Index: 935

Text #5

Max Range: 3.7003. Min Range: -3.7003

Max Act: 3.6338. Min Act: -0.1700

Data Index: 2978071 (Open Web Text)

Max Activating Token Index: 691

Text #6

Max Range: 3.7003. Min Range: -3.7003

Max Act: 3.6037. Min Act: -0.1700

Data Index: 1081601 (Open Web Text)

Max Activating Token Index: 239

Text #7

Max Range: 3.7003. Min Range: -3.7003

Max Act: 3.5826. Min Act: -0.1700

Data Index: 6926849 (Open Web Text)

Max Activating Token Index: 615

Text #8

Max Range: 3.7003. Min Range: -3.7003

Max Act: 3.5726. Min Act: -0.1700

Data Index: 3549476 (Open Web Text)

Max Activating Token Index: 723

Text #9

Max Range: 3.7003. Min Range: -3.7003

Max Act: 3.5632. Min Act: -0.1700

Data Index: 6090200 (Open Web Text)

Max Activating Token Index: 211

Text #10

Max Range: 3.7003. Min Range: -3.7003

Max Act: 3.5786. Min Act: -0.1700

Data Index: 8308425 (Open Web Text)

Max Activating Token Index: 513

Text #11

Max Range: 3.7003. Min Range: -3.7003

Max Act: 3.5498. Min Act: -0.1700

Data Index: 7108128 (Open Web Text)

Max Activating Token Index: 436

Text #12

Max Range: 3.7003. Min Range: -3.7003

Max Act: 3.5598. Min Act: -0.1700

Data Index: 3408379 (Open Web Text)

Max Activating Token Index: 522

Text #13

Max Range: 3.7003. Min Range: -3.7003

Max Act: 3.5367. Min Act: -0.1700

Data Index: 661417 (Open Web Text)

Max Activating Token Index: 746

Text #14

Max Range: 3.7003. Min Range: -3.7003

Max Act: 3.5392. Min Act: -0.1700

Data Index: 5378323 (Open Web Text)

Max Activating Token Index: 483

Text #15

Max Range: 3.7003. Min Range: -3.7003

Max Act: 3.5299. Min Act: -0.1700

Data Index: 3534861 (Open Web Text)

Max Activating Token Index: 426

Text #16

Max Range: 3.7003. Min Range: -3.7003

Max Act: 3.5435. Min Act: -0.1700

Data Index: 4511702 (Open Web Text)

Max Activating Token Index: 397

Text #17

Max Range: 3.7003. Min Range: -3.7003

Max Act: 3.5052. Min Act: -0.1700

Data Index: 2145550 (Open Web Text)

Max Activating Token Index: 600

Text #18

Max Range: 3.7003. Min Range: -3.7003

Max Act: 3.5059. Min Act: -0.1700

Data Index: 7113697 (Open Web Text)

Max Activating Token Index: 620

Text #19

Max Range: 3.7003. Min Range: -3.7003

Max Act: 3.5078. Min Act: -0.1700

Data Index: 8251803 (Open Web Text)

Max Activating Token Index: 485