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

Dataset: Open Web Text

Neuron 322 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: 3.8299. Min Range: -3.8299

Max Act: 3.8299. Min Act: -0.1700

Data Index: 8044565 (Open Web Text)

Max Activating Token Index: 523

Text #1

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.6933. Min Act: -0.1700

Data Index: 8818711 (Open Web Text)

Max Activating Token Index: 353

Text #2

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.7053. Min Act: -0.1700

Data Index: 713502 (Open Web Text)

Max Activating Token Index: 427

Text #3

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.6259. Min Act: -0.1700

Data Index: 3785100 (Open Web Text)

Max Activating Token Index: 685

Text #4

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.6063. Min Act: -0.1700

Data Index: 748093 (Open Web Text)

Max Activating Token Index: 191

Text #5

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.6065. Min Act: -0.1700

Data Index: 1802906 (Open Web Text)

Max Activating Token Index: 630

Text #6

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5771. Min Act: -0.1700

Data Index: 7173060 (Open Web Text)

Max Activating Token Index: 389

Text #7

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5826. Min Act: -0.1700

Data Index: 8005725 (Open Web Text)

Max Activating Token Index: 967

Text #8

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5899. Min Act: -0.1700

Data Index: 3091664 (Open Web Text)

Max Activating Token Index: 538

Text #9

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.6188. Min Act: -0.1700

Data Index: 990220 (Open Web Text)

Max Activating Token Index: 794

Text #10

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5568. Min Act: -0.1700

Data Index: 1519205 (Open Web Text)

Max Activating Token Index: 247

Text #11

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5477. Min Act: -0.1700

Data Index: 1610083 (Open Web Text)

Max Activating Token Index: 791

Text #12

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5311. Min Act: -0.1700

Data Index: 8472637 (Open Web Text)

Max Activating Token Index: 441

Text #13

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5426. Min Act: -0.1700

Data Index: 6720645 (Open Web Text)

Max Activating Token Index: 808

Text #14

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5331. Min Act: -0.1700

Data Index: 6563048 (Open Web Text)

Max Activating Token Index: 110

Text #15

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5428. Min Act: -0.1700

Data Index: 5966766 (Open Web Text)

Max Activating Token Index: 320

Text #16

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5667. Min Act: -0.1700

Data Index: 6161475 (Open Web Text)

Max Activating Token Index: 510

Text #17

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.4997. Min Act: -0.1700

Data Index: 4583189 (Open Web Text)

Max Activating Token Index: 378

Text #18

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5202. Min Act: -0.1700

Data Index: 6634027 (Open Web Text)

Max Activating Token Index: 173

Text #19

Max Range: 3.8299. Min Range: -3.8299

Max Act: 3.5142. Min Act: -0.1700

Data Index: 8640741 (Open Web Text)

Max Activating Token Index: 625