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

Dataset: Open Web Text

Neuron 104 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: 4.3280. Min Range: -4.3280

Max Act: 4.3280. Min Act: -0.1700

Data Index: 5500215 (Open Web Text)

Max Activating Token Index: 137

Text #1

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.1838. Min Act: -0.1700

Data Index: 2079271 (Open Web Text)

Max Activating Token Index: 811

Text #2

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.1797. Min Act: -0.1700

Data Index: 7851749 (Open Web Text)

Max Activating Token Index: 552

Text #3

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.1541. Min Act: -0.1700

Data Index: 1395667 (Open Web Text)

Max Activating Token Index: 582

Text #4

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.1159. Min Act: -0.1700

Data Index: 4685408 (Open Web Text)

Max Activating Token Index: 888

Text #5

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.1068. Min Act: -0.1700

Data Index: 3100098 (Open Web Text)

Max Activating Token Index: 262

Text #6

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.0327. Min Act: -0.1700

Data Index: 713505 (Open Web Text)

Max Activating Token Index: 875

Text #7

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.0593. Min Act: -0.1700

Data Index: 6655397 (Open Web Text)

Max Activating Token Index: 1015

Text #8

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.0083. Min Act: -0.1700

Data Index: 1641896 (Open Web Text)

Max Activating Token Index: 476

Text #9

Max Range: 4.3280. Min Range: -4.3280

Max Act: 3.9911. Min Act: -0.1700

Data Index: 2638831 (Open Web Text)

Max Activating Token Index: 497

Text #10

Max Range: 4.3280. Min Range: -4.3280

Max Act: 3.9625. Min Act: -0.1700

Data Index: 4646032 (Open Web Text)

Max Activating Token Index: 169

Text #11

Max Range: 4.3280. Min Range: -4.3280

Max Act: 3.9577. Min Act: -0.1700

Data Index: 4403124 (Open Web Text)

Max Activating Token Index: 936

Text #12

Max Range: 4.3280. Min Range: -4.3280

Max Act: 3.9481. Min Act: -0.1700

Data Index: 1663680 (Open Web Text)

Max Activating Token Index: 273

Text #13

Max Range: 4.3280. Min Range: -4.3280

Max Act: 3.9631. Min Act: -0.1700

Data Index: 4045281 (Open Web Text)

Max Activating Token Index: 376

Text #14

Max Range: 4.3280. Min Range: -4.3280

Max Act: 3.9358. Min Act: -0.1700

Data Index: 2251474 (Open Web Text)

Max Activating Token Index: 197

Text #15

Max Range: 4.3280. Min Range: -4.3280

Max Act: 3.9270. Min Act: -0.1700

Data Index: 2671399 (Open Web Text)

Max Activating Token Index: 642

Text #16

Max Range: 4.3280. Min Range: -4.3280

Max Act: 3.9137. Min Act: -0.1700

Data Index: 5950350 (Open Web Text)

Max Activating Token Index: 117

Text #17

Max Range: 4.3280. Min Range: -4.3280

Max Act: 3.9380. Min Act: -0.1700

Data Index: 5937 (Open Web Text)

Max Activating Token Index: 705

Text #18

Max Range: 4.3280. Min Range: -4.3280

Max Act: 3.9077. Min Act: -0.1700

Data Index: 4430104 (Open Web Text)

Max Activating Token Index: 400

Text #19

Max Range: 4.3280. Min Range: -4.3280

Max Act: 3.9222. Min Act: -0.1700

Data Index: 7512954 (Open Web Text)

Max Activating Token Index: 356