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

Dataset: Open Web Text

Neuron 2646 in Layer 5

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: 5.2750. Min Range: -5.2750

Max Act: 5.2750. Min Act: -0.1700

Data Index: 259023 (Open Web Text)

Max Activating Token Index: 631

Text #1

Max Range: 5.2750. Min Range: -5.2750

Max Act: 5.2181. Min Act: -0.1700

Data Index: 1839179 (Open Web Text)

Max Activating Token Index: 840

Text #2

Max Range: 5.2750. Min Range: -5.2750

Max Act: 5.2140. Min Act: -0.1700

Data Index: 5737400 (Open Web Text)

Max Activating Token Index: 497

Text #3

Max Range: 5.2750. Min Range: -5.2750

Max Act: 5.1768. Min Act: -0.1700

Data Index: 7019205 (Open Web Text)

Max Activating Token Index: 776

Text #4

Max Range: 5.2750. Min Range: -5.2750

Max Act: 5.1522. Min Act: -0.1700

Data Index: 7352675 (Open Web Text)

Max Activating Token Index: 165

Text #5

Max Range: 5.2750. Min Range: -5.2750

Max Act: 5.1176. Min Act: -0.1700

Data Index: 2099264 (Open Web Text)

Max Activating Token Index: 228

Text #6

Max Range: 5.2750. Min Range: -5.2750

Max Act: 5.0695. Min Act: -0.1700

Data Index: 6531275 (Open Web Text)

Max Activating Token Index: 532

Text #7

Max Range: 5.2750. Min Range: -5.2750

Max Act: 5.1170. Min Act: -0.1700

Data Index: 6743230 (Open Web Text)

Max Activating Token Index: 1018

Text #8

Max Range: 5.2750. Min Range: -5.2750

Max Act: 5.1219. Min Act: -0.1700

Data Index: 1336583 (Open Web Text)

Max Activating Token Index: 105

Text #9

Max Range: 5.2750. Min Range: -5.2750

Max Act: 5.0544. Min Act: -0.1700

Data Index: 5174314 (Open Web Text)

Max Activating Token Index: 259

Text #10

Max Range: 5.2750. Min Range: -5.2750

Max Act: 5.0912. Min Act: -0.1700

Data Index: 2129106 (Open Web Text)

Max Activating Token Index: 125

Text #11

Max Range: 5.2750. Min Range: -5.2750

Max Act: 5.0440. Min Act: -0.1700

Data Index: 7317549 (Open Web Text)

Max Activating Token Index: 116

Text #12

Max Range: 5.2750. Min Range: -5.2750

Max Act: 5.0227. Min Act: -0.1700

Data Index: 4713185 (Open Web Text)

Max Activating Token Index: 190

Text #13

Max Range: 5.2750. Min Range: -5.2750

Max Act: 5.0148. Min Act: -0.1700

Data Index: 2419907 (Open Web Text)

Max Activating Token Index: 1007

Text #14

Max Range: 5.2750. Min Range: -5.2750

Max Act: 4.9724. Min Act: -0.1700

Data Index: 2449597 (Open Web Text)

Max Activating Token Index: 696

Text #15

Max Range: 5.2750. Min Range: -5.2750

Max Act: 5.0340. Min Act: -0.1700

Data Index: 927857 (Open Web Text)

Max Activating Token Index: 376

Text #16

Max Range: 5.2750. Min Range: -5.2750

Max Act: 5.0336. Min Act: -0.1700

Data Index: 6568614 (Open Web Text)

Max Activating Token Index: 800

Text #17

Max Range: 5.2750. Min Range: -5.2750

Max Act: 5.0559. Min Act: -0.1700

Data Index: 4764670 (Open Web Text)

Max Activating Token Index: 559

Text #18

Max Range: 5.2750. Min Range: -5.2750

Max Act: 4.9431. Min Act: -0.1700

Data Index: 2581925 (Open Web Text)

Max Activating Token Index: 27

Text #19

Max Range: 5.2750. Min Range: -5.2750

Max Act: 4.9587. Min Act: -0.1700

Data Index: 6457091 (Open Web Text)

Max Activating Token Index: 328