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

Dataset: Open Web Text

Neuron 3044 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: 4.0770. Min Range: -4.0770

Max Act: 4.0770. Min Act: -0.1700

Data Index: 74892 (Open Web Text)

Max Activating Token Index: 861

Text #1

Max Range: 4.0770. Min Range: -4.0770

Max Act: 3.8650. Min Act: -0.1700

Data Index: 6923630 (Open Web Text)

Max Activating Token Index: 594

Text #2

Max Range: 4.0770. Min Range: -4.0770

Max Act: 3.8356. Min Act: -0.1700

Data Index: 2030511 (Open Web Text)

Max Activating Token Index: 640

Text #3

Max Range: 4.0770. Min Range: -4.0770

Max Act: 3.7542. Min Act: -0.1700

Data Index: 955511 (Open Web Text)

Max Activating Token Index: 346

Text #4

Max Range: 4.0770. Min Range: -4.0770

Max Act: 3.6963. Min Act: -0.1700

Data Index: 2211573 (Open Web Text)

Max Activating Token Index: 239

Text #5

Max Range: 4.0770. Min Range: -4.0770

Max Act: 3.6419. Min Act: -0.1700

Data Index: 3901975 (Open Web Text)

Max Activating Token Index: 574

Text #6

Max Range: 4.0770. Min Range: -4.0770

Max Act: 3.6315. Min Act: -0.1700

Data Index: 4398976 (Open Web Text)

Max Activating Token Index: 377

Text #7

Max Range: 4.0770. Min Range: -4.0770

Max Act: 3.6100. Min Act: -0.1700

Data Index: 4339159 (Open Web Text)

Max Activating Token Index: 250

Text #8

Max Range: 4.0770. Min Range: -4.0770

Max Act: 3.5933. Min Act: -0.1700

Data Index: 6151615 (Open Web Text)

Max Activating Token Index: 862

Text #9

Max Range: 4.0770. Min Range: -4.0770

Max Act: 3.5757. Min Act: -0.1700

Data Index: 7011367 (Open Web Text)

Max Activating Token Index: 603

Text #10

Max Range: 4.0770. Min Range: -4.0770

Max Act: 3.6612. Min Act: -0.1700

Data Index: 74621 (Open Web Text)

Max Activating Token Index: 665

Text #11

Max Range: 4.0770. Min Range: -4.0770

Max Act: 3.5758. Min Act: -0.1700

Data Index: 3717124 (Open Web Text)

Max Activating Token Index: 807

Text #12

Max Range: 4.0770. Min Range: -4.0770

Max Act: 3.5671. Min Act: -0.1700

Data Index: 8317809 (Open Web Text)

Max Activating Token Index: 591

Text #13

Max Range: 4.0770. Min Range: -4.0770

Max Act: 3.5400. Min Act: -0.1700

Data Index: 7439042 (Open Web Text)

Max Activating Token Index: 904

Text #14

Max Range: 4.0770. Min Range: -4.0770

Max Act: 3.5975. Min Act: -0.1700

Data Index: 6092384 (Open Web Text)

Max Activating Token Index: 287

Text #15

Max Range: 4.0770. Min Range: -4.0770

Max Act: 3.6121. Min Act: -0.1700

Data Index: 6750211 (Open Web Text)

Max Activating Token Index: 490

Text #16

Max Range: 4.0770. Min Range: -4.0770

Max Act: 3.5540. Min Act: -0.1700

Data Index: 1847608 (Open Web Text)

Max Activating Token Index: 274

Text #17

Max Range: 4.0770. Min Range: -4.0770

Max Act: 3.5529. Min Act: -0.1700

Data Index: 4698217 (Open Web Text)

Max Activating Token Index: 570

Text #18

Max Range: 4.0770. Min Range: -4.0770

Max Act: 3.5136. Min Act: -0.1700

Data Index: 2919158 (Open Web Text)

Max Activating Token Index: 153

Text #19

Max Range: 4.0770. Min Range: -4.0770

Max Act: 3.5368. Min Act: -0.1700

Data Index: 5519350 (Open Web Text)

Max Activating Token Index: 313