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

Dataset: Open Web Text

Neuron 1600 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: 3.9021. Min Range: -3.9021

Max Act: 3.9021. Min Act: -0.1700

Data Index: 7760441 (Open Web Text)

Max Activating Token Index: 888

Text #1

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.5472. Min Act: -0.1700

Data Index: 7695202 (Open Web Text)

Max Activating Token Index: 815

Text #2

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.5184. Min Act: -0.1700

Data Index: 8139285 (Open Web Text)

Max Activating Token Index: 148

Text #3

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.5064. Min Act: -0.1700

Data Index: 2245243 (Open Web Text)

Max Activating Token Index: 742

Text #4

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.5351. Min Act: -0.1700

Data Index: 761804 (Open Web Text)

Max Activating Token Index: 194

Text #5

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.5168. Min Act: -0.1700

Data Index: 556190 (Open Web Text)

Max Activating Token Index: 816

Text #6

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.4883. Min Act: -0.1700

Data Index: 1586889 (Open Web Text)

Max Activating Token Index: 545

Text #7

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.4638. Min Act: -0.1700

Data Index: 7933125 (Open Web Text)

Max Activating Token Index: 762

Text #8

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.4474. Min Act: -0.1700

Data Index: 2908062 (Open Web Text)

Max Activating Token Index: 430

Text #9

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.4312. Min Act: -0.1700

Data Index: 2971668 (Open Web Text)

Max Activating Token Index: 875

Text #10

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.4291. Min Act: -0.1700

Data Index: 5770423 (Open Web Text)

Max Activating Token Index: 565

Text #11

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.4203. Min Act: -0.1700

Data Index: 2731386 (Open Web Text)

Max Activating Token Index: 691

Text #12

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.4598. Min Act: -0.1700

Data Index: 3779426 (Open Web Text)

Max Activating Token Index: 413

Text #13

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.4234. Min Act: -0.1700

Data Index: 7919408 (Open Web Text)

Max Activating Token Index: 63

Text #14

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.4165. Min Act: -0.1700

Data Index: 7944014 (Open Web Text)

Max Activating Token Index: 649

Text #15

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.4254. Min Act: -0.1700

Data Index: 7990694 (Open Web Text)

Max Activating Token Index: 228

Text #16

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.4342. Min Act: -0.1700

Data Index: 2915789 (Open Web Text)

Max Activating Token Index: 376

Text #17

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.4011. Min Act: -0.1700

Data Index: 5701324 (Open Web Text)

Max Activating Token Index: 656

Text #18

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.3958. Min Act: -0.1700

Data Index: 1093571 (Open Web Text)

Max Activating Token Index: 741

Text #19

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.4096. Min Act: -0.1700

Data Index: 8413184 (Open Web Text)

Max Activating Token Index: 433