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

Dataset: Open Web Text

Neuron 2596 in Layer 2

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: 3.7056. Min Range: -3.7056

Max Act: 3.6858. Min Act: -0.1700

Data Index: 781061 (Open Web Text)

Max Activating Token Index: 395

Text #1

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.7056. Min Act: -0.1700

Data Index: 4574530 (Open Web Text)

Max Activating Token Index: 776

Text #2

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.6834. Min Act: -0.1700

Data Index: 3456086 (Open Web Text)

Max Activating Token Index: 468

Text #3

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.6678. Min Act: -0.1700

Data Index: 4085252 (Open Web Text)

Max Activating Token Index: 843

Text #4

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.6070. Min Act: -0.1700

Data Index: 3056816 (Open Web Text)

Max Activating Token Index: 447

Text #5

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5889. Min Act: -0.1700

Data Index: 6376155 (Open Web Text)

Max Activating Token Index: 460

Text #6

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5618. Min Act: -0.1700

Data Index: 2922946 (Open Web Text)

Max Activating Token Index: 489

Text #7

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5782. Min Act: -0.1700

Data Index: 3006692 (Open Web Text)

Max Activating Token Index: 439

Text #8

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5839. Min Act: -0.1700

Data Index: 6192329 (Open Web Text)

Max Activating Token Index: 1007

Text #9

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5623. Min Act: -0.1700

Data Index: 5602597 (Open Web Text)

Max Activating Token Index: 42

Text #10

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5706. Min Act: -0.1700

Data Index: 8789657 (Open Web Text)

Max Activating Token Index: 379

Text #11

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5676. Min Act: -0.1700

Data Index: 8623646 (Open Web Text)

Max Activating Token Index: 495

Text #12

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5388. Min Act: -0.1700

Data Index: 1245855 (Open Web Text)

Max Activating Token Index: 589

Text #13

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5502. Min Act: -0.1700

Data Index: 7649081 (Open Web Text)

Max Activating Token Index: 811

Text #14

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5810. Min Act: -0.1700

Data Index: 6488456 (Open Web Text)

Max Activating Token Index: 367

Text #15

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5451. Min Act: -0.1700

Data Index: 6380895 (Open Web Text)

Max Activating Token Index: 426

Text #16

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.4898. Min Act: -0.1700

Data Index: 5019856 (Open Web Text)

Max Activating Token Index: 362

Text #17

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5086. Min Act: -0.1700

Data Index: 5062163 (Open Web Text)

Max Activating Token Index: 237

Text #18

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5061. Min Act: -0.1700

Data Index: 6115702 (Open Web Text)

Max Activating Token Index: 487

Text #19

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5186. Min Act: -0.1700

Data Index: 6266314 (Open Web Text)

Max Activating Token Index: 219