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

Dataset: Open Web Text

Neuron 108 in Layer 4

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: 4.1211. Min Range: -4.1211

Max Act: 4.1211. Min Act: -0.1700

Data Index: 3130132 (Open Web Text)

Max Activating Token Index: 803

Text #1

Max Range: 4.1211. Min Range: -4.1211

Max Act: 4.0030. Min Act: -0.1700

Data Index: 86309 (Open Web Text)

Max Activating Token Index: 600

Text #2

Max Range: 4.1211. Min Range: -4.1211

Max Act: 4.0083. Min Act: -0.1700

Data Index: 4288398 (Open Web Text)

Max Activating Token Index: 466

Text #3

Max Range: 4.1211. Min Range: -4.1211

Max Act: 3.8540. Min Act: -0.1700

Data Index: 6222642 (Open Web Text)

Max Activating Token Index: 1009

Text #4

Max Range: 4.1211. Min Range: -4.1211

Max Act: 3.8823. Min Act: -0.1700

Data Index: 1769110 (Open Web Text)

Max Activating Token Index: 606

Text #5

Max Range: 4.1211. Min Range: -4.1211

Max Act: 3.8347. Min Act: -0.1700

Data Index: 5426505 (Open Web Text)

Max Activating Token Index: 451

Text #6

Max Range: 4.1211. Min Range: -4.1211

Max Act: 3.8852. Min Act: -0.1700

Data Index: 5289557 (Open Web Text)

Max Activating Token Index: 65

Text #7

Max Range: 4.1211. Min Range: -4.1211

Max Act: 3.8649. Min Act: -0.1700

Data Index: 8127346 (Open Web Text)

Max Activating Token Index: 510

Text #8

Max Range: 4.1211. Min Range: -4.1211

Max Act: 3.8136. Min Act: -0.1700

Data Index: 6356132 (Open Web Text)

Max Activating Token Index: 480

Text #9

Max Range: 4.1211. Min Range: -4.1211

Max Act: 3.8169. Min Act: -0.1700

Data Index: 3383405 (Open Web Text)

Max Activating Token Index: 634

Text #10

Max Range: 4.1211. Min Range: -4.1211

Max Act: 3.7713. Min Act: -0.1700

Data Index: 5347397 (Open Web Text)

Max Activating Token Index: 631

Text #11

Max Range: 4.1211. Min Range: -4.1211

Max Act: 3.7535. Min Act: -0.1700

Data Index: 1202041 (Open Web Text)

Max Activating Token Index: 879

Text #12

Max Range: 4.1211. Min Range: -4.1211

Max Act: 3.7758. Min Act: -0.1700

Data Index: 6456298 (Open Web Text)

Max Activating Token Index: 655

Text #13

Max Range: 4.1211. Min Range: -4.1211

Max Act: 3.7345. Min Act: -0.1700

Data Index: 3362662 (Open Web Text)

Max Activating Token Index: 421

Text #14

Max Range: 4.1211. Min Range: -4.1211

Max Act: 3.6654. Min Act: -0.1700

Data Index: 7251409 (Open Web Text)

Max Activating Token Index: 257

Text #15

Max Range: 4.1211. Min Range: -4.1211

Max Act: 3.7669. Min Act: -0.1700

Data Index: 7009277 (Open Web Text)

Max Activating Token Index: 850

Text #16

Max Range: 4.1211. Min Range: -4.1211

Max Act: 3.7340. Min Act: -0.1700

Data Index: 5438882 (Open Web Text)

Max Activating Token Index: 400

Text #17

Max Range: 4.1211. Min Range: -4.1211

Max Act: 3.6934. Min Act: -0.1700

Data Index: 6474429 (Open Web Text)

Max Activating Token Index: 167

Text #18

Max Range: 4.1211. Min Range: -4.1211

Max Act: 3.6287. Min Act: -0.1700

Data Index: 1335394 (Open Web Text)

Max Activating Token Index: 1006

Text #19

Max Range: 4.1211. Min Range: -4.1211

Max Act: 3.7249. Min Act: -0.1700

Data Index: 6374466 (Open Web Text)

Max Activating Token Index: 680