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

Dataset: Open Web Text

Neuron 1651 in Layer 6

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: 3.1178. Min Range: -3.1178

Max Act: 3.1178. Min Act: -0.1700

Data Index: 4856077 (Open Web Text)

Max Activating Token Index: 129

Text #1

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.9540. Min Act: -0.1700

Data Index: 4981091 (Open Web Text)

Max Activating Token Index: 355

Text #2

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.9250. Min Act: -0.1700

Data Index: 6724028 (Open Web Text)

Max Activating Token Index: 975

Text #3

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.8673. Min Act: -0.1700

Data Index: 3384659 (Open Web Text)

Max Activating Token Index: 872

Text #4

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.8285. Min Act: -0.1700

Data Index: 8782380 (Open Web Text)

Max Activating Token Index: 731

Text #5

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.8012. Min Act: -0.1700

Data Index: 707387 (Open Web Text)

Max Activating Token Index: 800

Text #6

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.7862. Min Act: -0.1700

Data Index: 6278743 (Open Web Text)

Max Activating Token Index: 882

Text #7

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.7830. Min Act: -0.1700

Data Index: 7880801 (Open Web Text)

Max Activating Token Index: 433

Text #8

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.7932. Min Act: -0.1700

Data Index: 6479746 (Open Web Text)

Max Activating Token Index: 243

Text #9

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.7663. Min Act: -0.1700

Data Index: 3935050 (Open Web Text)

Max Activating Token Index: 859

Text #10

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.7710. Min Act: -0.1700

Data Index: 6165231 (Open Web Text)

Max Activating Token Index: 399

Text #11

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.7576. Min Act: -0.1700

Data Index: 3672247 (Open Web Text)

Max Activating Token Index: 304

Text #12

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.7404. Min Act: -0.1700

Data Index: 3665219 (Open Web Text)

Max Activating Token Index: 519

Text #13

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.7254. Min Act: -0.1700

Data Index: 4132238 (Open Web Text)

Max Activating Token Index: 550

Text #14

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.7388. Min Act: -0.1700

Data Index: 1577498 (Open Web Text)

Max Activating Token Index: 292

Text #15

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.7393. Min Act: -0.1700

Data Index: 1721714 (Open Web Text)

Max Activating Token Index: 705

Text #16

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.7213. Min Act: -0.1700

Data Index: 7842152 (Open Web Text)

Max Activating Token Index: 908

Text #17

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.7183. Min Act: -0.1700

Data Index: 6475432 (Open Web Text)

Max Activating Token Index: 664

Text #18

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.7354. Min Act: -0.1700

Data Index: 4138009 (Open Web Text)

Max Activating Token Index: 771

Text #19

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.7324. Min Act: -0.1700

Data Index: 381582 (Open Web Text)

Max Activating Token Index: 419