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

Dataset: Open Web Text

Neuron 487 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: 5.0391. Min Range: -5.0391

Max Act: 5.0391. Min Act: -0.1700

Data Index: 3762482 (Open Web Text)

Max Activating Token Index: 750

Text #1

Max Range: 5.0391. Min Range: -5.0391

Max Act: 5.0335. Min Act: -0.1700

Data Index: 8774685 (Open Web Text)

Max Activating Token Index: 506

Text #2

Max Range: 5.0391. Min Range: -5.0391

Max Act: 5.0150. Min Act: -0.1700

Data Index: 3166170 (Open Web Text)

Max Activating Token Index: 265

Text #3

Max Range: 5.0391. Min Range: -5.0391

Max Act: 5.0034. Min Act: -0.1700

Data Index: 2929884 (Open Web Text)

Max Activating Token Index: 354

Text #4

Max Range: 5.0391. Min Range: -5.0391

Max Act: 4.9904. Min Act: -0.1700

Data Index: 3652227 (Open Web Text)

Max Activating Token Index: 102

Text #5

Max Range: 5.0391. Min Range: -5.0391

Max Act: 4.9814. Min Act: -0.1700

Data Index: 431268 (Open Web Text)

Max Activating Token Index: 176

Text #6

Max Range: 5.0391. Min Range: -5.0391

Max Act: 5.0088. Min Act: -0.1700

Data Index: 2168320 (Open Web Text)

Max Activating Token Index: 311

Text #7

Max Range: 5.0391. Min Range: -5.0391

Max Act: 4.9958. Min Act: -0.1700

Data Index: 4240765 (Open Web Text)

Max Activating Token Index: 463

Text #8

Max Range: 5.0391. Min Range: -5.0391

Max Act: 5.0031. Min Act: -0.1700

Data Index: 2419970 (Open Web Text)

Max Activating Token Index: 251

Text #9

Max Range: 5.0391. Min Range: -5.0391

Max Act: 4.9887. Min Act: -0.1700

Data Index: 7676204 (Open Web Text)

Max Activating Token Index: 294

Text #10

Max Range: 5.0391. Min Range: -5.0391

Max Act: 4.9491. Min Act: -0.1700

Data Index: 3504770 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 5.0391. Min Range: -5.0391

Max Act: 4.9502. Min Act: -0.1700

Data Index: 2876343 (Open Web Text)

Max Activating Token Index: 106

Text #12

Max Range: 5.0391. Min Range: -5.0391

Max Act: 4.9624. Min Act: -0.1700

Data Index: 259226 (Open Web Text)

Max Activating Token Index: 200

Text #13

Max Range: 5.0391. Min Range: -5.0391

Max Act: 4.9596. Min Act: -0.1700

Data Index: 6979215 (Open Web Text)

Max Activating Token Index: 479

Text #14

Max Range: 5.0391. Min Range: -5.0391

Max Act: 4.9664. Min Act: -0.1700

Data Index: 1029402 (Open Web Text)

Max Activating Token Index: 589

Text #15

Max Range: 5.0391. Min Range: -5.0391

Max Act: 4.9648. Min Act: -0.1700

Data Index: 913005 (Open Web Text)

Max Activating Token Index: 606

Text #16

Max Range: 5.0391. Min Range: -5.0391

Max Act: 4.9332. Min Act: -0.1700

Data Index: 2632956 (Open Web Text)

Max Activating Token Index: 430

Text #17

Max Range: 5.0391. Min Range: -5.0391

Max Act: 4.9531. Min Act: -0.1700

Data Index: 2816745 (Open Web Text)

Max Activating Token Index: 626

Text #18

Max Range: 5.0391. Min Range: -5.0391

Max Act: 4.9309. Min Act: -0.1700

Data Index: 324855 (Open Web Text)

Max Activating Token Index: 41

Text #19

Max Range: 5.0391. Min Range: -5.0391

Max Act: 4.9153. Min Act: -0.1700

Data Index: 1306683 (Open Web Text)

Max Activating Token Index: 285