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

Dataset: Open Web Text

Neuron 172 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: 3.9700. Min Range: -3.9700

Max Act: 3.9700. Min Act: -0.1700

Data Index: 2228379 (Open Web Text)

Max Activating Token Index: 55

Text #1

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.9331. Min Act: -0.1700

Data Index: 2296664 (Open Web Text)

Max Activating Token Index: 976

Text #2

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.9293. Min Act: -0.1700

Data Index: 2365294 (Open Web Text)

Max Activating Token Index: 656

Text #3

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.9019. Min Act: -0.1700

Data Index: 7769868 (Open Web Text)

Max Activating Token Index: 783

Text #4

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.8389. Min Act: -0.1700

Data Index: 7640105 (Open Web Text)

Max Activating Token Index: 227

Text #5

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.8515. Min Act: -0.1700

Data Index: 37512 (Open Web Text)

Max Activating Token Index: 679

Text #6

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.8478. Min Act: -0.1700

Data Index: 8185164 (Open Web Text)

Max Activating Token Index: 796

Text #7

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7982. Min Act: -0.1700

Data Index: 6369652 (Open Web Text)

Max Activating Token Index: 521

Text #8

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7698. Min Act: -0.1700

Data Index: 4885730 (Open Web Text)

Max Activating Token Index: 175

Text #9

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7541. Min Act: -0.1700

Data Index: 5920124 (Open Web Text)

Max Activating Token Index: 112

Text #10

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7437. Min Act: -0.1700

Data Index: 7348557 (Open Web Text)

Max Activating Token Index: 503

Text #11

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7400. Min Act: -0.1700

Data Index: 4788466 (Open Web Text)

Max Activating Token Index: 141

Text #12

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7240. Min Act: -0.1700

Data Index: 6548696 (Open Web Text)

Max Activating Token Index: 312

Text #13

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7081. Min Act: -0.1700

Data Index: 8185995 (Open Web Text)

Max Activating Token Index: 756

Text #14

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7158. Min Act: -0.1700

Data Index: 882964 (Open Web Text)

Max Activating Token Index: 268

Text #15

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.6952. Min Act: -0.1700

Data Index: 1442556 (Open Web Text)

Max Activating Token Index: 635

Text #16

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.6965. Min Act: -0.1700

Data Index: 7421854 (Open Web Text)

Max Activating Token Index: 370

Text #17

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.6933. Min Act: -0.1700

Data Index: 6954613 (Open Web Text)

Max Activating Token Index: 496

Text #18

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7190. Min Act: -0.1700

Data Index: 6738464 (Open Web Text)

Max Activating Token Index: 316

Text #19

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.6933. Min Act: -0.1700

Data Index: 5164482 (Open Web Text)

Max Activating Token Index: 776