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

Dataset: Open Web Text

Neuron 2495 in Layer 1

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: 3.8563. Min Range: -3.8563

Max Act: 3.8473. Min Act: -0.1700

Data Index: 3182371 (Open Web Text)

Max Activating Token Index: 414

Text #1

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.8563. Min Act: -0.1700

Data Index: 25592 (Open Web Text)

Max Activating Token Index: 461

Text #2

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.8547. Min Act: -0.1700

Data Index: 2424678 (Open Web Text)

Max Activating Token Index: 472

Text #3

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.8391. Min Act: -0.1700

Data Index: 5828693 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.8065. Min Act: -0.1700

Data Index: 5077640 (Open Web Text)

Max Activating Token Index: 479

Text #5

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.8023. Min Act: -0.1700

Data Index: 5565578 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.7992. Min Act: -0.1700

Data Index: 5221953 (Open Web Text)

Max Activating Token Index: 210

Text #7

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.8144. Min Act: -0.1700

Data Index: 5000241 (Open Web Text)

Max Activating Token Index: 123

Text #8

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.8320. Min Act: -0.1700

Data Index: 1934711 (Open Web Text)

Max Activating Token Index: 577

Text #9

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.8170. Min Act: -0.1700

Data Index: 8506365 (Open Web Text)

Max Activating Token Index: 447

Text #10

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.8170. Min Act: -0.1700

Data Index: 7002508 (Open Web Text)

Max Activating Token Index: 391

Text #11

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.8356. Min Act: -0.1700

Data Index: 5959795 (Open Web Text)

Max Activating Token Index: 733

Text #12

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.7941. Min Act: -0.1700

Data Index: 4907955 (Open Web Text)

Max Activating Token Index: 154

Text #13

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.7971. Min Act: -0.1700

Data Index: 4732432 (Open Web Text)

Max Activating Token Index: 451

Text #14

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.7755. Min Act: -0.1700

Data Index: 4186223 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.7779. Min Act: -0.1700

Data Index: 2216235 (Open Web Text)

Max Activating Token Index: 631

Text #16

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.7754. Min Act: -0.1700

Data Index: 2577965 (Open Web Text)

Max Activating Token Index: 318

Text #17

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.8019. Min Act: -0.1700

Data Index: 2767095 (Open Web Text)

Max Activating Token Index: 257

Text #18

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.7787. Min Act: -0.1700

Data Index: 5625550 (Open Web Text)

Max Activating Token Index: 505

Text #19

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.7825. Min Act: -0.1700

Data Index: 5678556 (Open Web Text)

Max Activating Token Index: 484