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

Dataset: Open Web Text

Neuron 255 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: 3.3712. Min Range: -3.3712

Max Act: 3.3712. Min Act: -0.1700

Data Index: 2126582 (Open Web Text)

Max Activating Token Index: 501

Text #1

Max Range: 3.3712. Min Range: -3.3712

Max Act: 3.3293. Min Act: -0.1700

Data Index: 6814138 (Open Web Text)

Max Activating Token Index: 73

Text #2

Max Range: 3.3712. Min Range: -3.3712

Max Act: 3.3280. Min Act: -0.1700

Data Index: 4100867 (Open Web Text)

Max Activating Token Index: 339

Text #3

Max Range: 3.3712. Min Range: -3.3712

Max Act: 3.2834. Min Act: -0.1700

Data Index: 2687566 (Open Web Text)

Max Activating Token Index: 636

Text #4

Max Range: 3.3712. Min Range: -3.3712

Max Act: 3.2829. Min Act: -0.1700

Data Index: 2687562 (Open Web Text)

Max Activating Token Index: 594

Text #5

Max Range: 3.3712. Min Range: -3.3712

Max Act: 3.2700. Min Act: -0.1700

Data Index: 7140910 (Open Web Text)

Max Activating Token Index: 338

Text #6

Max Range: 3.3712. Min Range: -3.3712

Max Act: 3.2923. Min Act: -0.1700

Data Index: 668957 (Open Web Text)

Max Activating Token Index: 172

Text #7

Max Range: 3.3712. Min Range: -3.3712

Max Act: 3.2718. Min Act: -0.1700

Data Index: 2687563 (Open Web Text)

Max Activating Token Index: 678

Text #8

Max Range: 3.3712. Min Range: -3.3712

Max Act: 3.2305. Min Act: -0.1700

Data Index: 2859979 (Open Web Text)

Max Activating Token Index: 672

Text #9

Max Range: 3.3712. Min Range: -3.3712

Max Act: 3.2493. Min Act: -0.1700

Data Index: 2687568 (Open Web Text)

Max Activating Token Index: 275

Text #10

Max Range: 3.3712. Min Range: -3.3712

Max Act: 3.2488. Min Act: -0.1700

Data Index: 2687565 (Open Web Text)

Max Activating Token Index: 410

Text #11

Max Range: 3.3712. Min Range: -3.3712

Max Act: 3.2602. Min Act: -0.1700

Data Index: 8444234 (Open Web Text)

Max Activating Token Index: 470

Text #12

Max Range: 3.3712. Min Range: -3.3712

Max Act: 3.2155. Min Act: -0.1700

Data Index: 2687569 (Open Web Text)

Max Activating Token Index: 705

Text #13

Max Range: 3.3712. Min Range: -3.3712

Max Act: 3.2178. Min Act: -0.1700

Data Index: 4460872 (Open Web Text)

Max Activating Token Index: 388

Text #14

Max Range: 3.3712. Min Range: -3.3712

Max Act: 3.2129. Min Act: -0.1700

Data Index: 2531050 (Open Web Text)

Max Activating Token Index: 249

Text #15

Max Range: 3.3712. Min Range: -3.3712

Max Act: 3.2041. Min Act: -0.1700

Data Index: 2096947 (Open Web Text)

Max Activating Token Index: 229

Text #16

Max Range: 3.3712. Min Range: -3.3712

Max Act: 3.2257. Min Act: -0.1700

Data Index: 2845661 (Open Web Text)

Max Activating Token Index: 150

Text #17

Max Range: 3.3712. Min Range: -3.3712

Max Act: 3.2040. Min Act: -0.1700

Data Index: 2933830 (Open Web Text)

Max Activating Token Index: 681

Text #18

Max Range: 3.3712. Min Range: -3.3712

Max Act: 3.2186. Min Act: -0.1700

Data Index: 2859980 (Open Web Text)

Max Activating Token Index: 500

Text #19

Max Range: 3.3712. Min Range: -3.3712

Max Act: 3.1893. Min Act: -0.1700

Data Index: 2687564 (Open Web Text)

Max Activating Token Index: 81