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

Dataset: Open Web Text

Neuron 2422 in Layer 0

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: 3.9554. Min Range: -3.9554

Max Act: 3.9394. Min Act: -0.1700

Data Index: 117544 (Open Web Text)

Max Activating Token Index: 637

Text #1

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.9554. Min Act: -0.1700

Data Index: 3407433 (Open Web Text)

Max Activating Token Index: 884

Text #2

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.9257. Min Act: -0.1700

Data Index: 175890 (Open Web Text)

Max Activating Token Index: 383

Text #3

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.9142. Min Act: -0.1700

Data Index: 534222 (Open Web Text)

Max Activating Token Index: 384

Text #4

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.9090. Min Act: -0.1700

Data Index: 5639104 (Open Web Text)

Max Activating Token Index: 33

Text #5

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.8991. Min Act: -0.1700

Data Index: 6143614 (Open Web Text)

Max Activating Token Index: 468

Text #6

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.8640. Min Act: -0.1700

Data Index: 2910680 (Open Web Text)

Max Activating Token Index: 79

Text #7

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.8686. Min Act: -0.1700

Data Index: 5294986 (Open Web Text)

Max Activating Token Index: 681

Text #8

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.8824. Min Act: -0.1700

Data Index: 4665140 (Open Web Text)

Max Activating Token Index: 23

Text #9

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.8655. Min Act: -0.1700

Data Index: 4655830 (Open Web Text)

Max Activating Token Index: 816

Text #10

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.8855. Min Act: -0.1700

Data Index: 6631995 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.8904. Min Act: -0.1700

Data Index: 6477632 (Open Web Text)

Max Activating Token Index: 265

Text #12

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.8756. Min Act: -0.1700

Data Index: 4075749 (Open Web Text)

Max Activating Token Index: 596

Text #13

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.8616. Min Act: -0.1700

Data Index: 6354574 (Open Web Text)

Max Activating Token Index: 265

Text #14

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.8877. Min Act: -0.1700

Data Index: 6342821 (Open Web Text)

Max Activating Token Index: 373

Text #15

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.8466. Min Act: -0.1700

Data Index: 4876800 (Open Web Text)

Max Activating Token Index: 839

Text #16

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.8346. Min Act: -0.1700

Data Index: 1934858 (Open Web Text)

Max Activating Token Index: 332

Text #17

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.8366. Min Act: -0.1700

Data Index: 5593073 (Open Web Text)

Max Activating Token Index: 251

Text #18

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.8298. Min Act: -0.1700

Data Index: 789843 (Open Web Text)

Max Activating Token Index: 258

Text #19

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.8516. Min Act: -0.1700

Data Index: 5774911 (Open Web Text)

Max Activating Token Index: 390