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

Dataset: Open Web Text

Neuron 2506 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: 4.3329. Min Range: -4.3329

Max Act: 4.3329. Min Act: -0.1700

Data Index: 7821230 (Open Web Text)

Max Activating Token Index: 284

Text #1

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.2842. Min Act: -0.1700

Data Index: 1424424 (Open Web Text)

Max Activating Token Index: 274

Text #2

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.2622. Min Act: -0.1700

Data Index: 6243472 (Open Web Text)

Max Activating Token Index: 135

Text #3

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.2109. Min Act: -0.1700

Data Index: 265622 (Open Web Text)

Max Activating Token Index: 929

Text #4

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.2552. Min Act: -0.1700

Data Index: 8177875 (Open Web Text)

Max Activating Token Index: 637

Text #5

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.2112. Min Act: -0.1700

Data Index: 7296953 (Open Web Text)

Max Activating Token Index: 233

Text #6

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.2076. Min Act: -0.1700

Data Index: 1810769 (Open Web Text)

Max Activating Token Index: 191

Text #7

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.1959. Min Act: -0.1700

Data Index: 7296955 (Open Web Text)

Max Activating Token Index: 252

Text #8

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.1702. Min Act: -0.1700

Data Index: 4826275 (Open Web Text)

Max Activating Token Index: 911

Text #9

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.1533. Min Act: -0.1700

Data Index: 627259 (Open Web Text)

Max Activating Token Index: 772

Text #10

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.1358. Min Act: -0.1700

Data Index: 8326697 (Open Web Text)

Max Activating Token Index: 199

Text #11

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.1471. Min Act: -0.1700

Data Index: 6948677 (Open Web Text)

Max Activating Token Index: 130

Text #12

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.1061. Min Act: -0.1700

Data Index: 7296952 (Open Web Text)

Max Activating Token Index: 995

Text #13

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.1080. Min Act: -0.1700

Data Index: 7296954 (Open Web Text)

Max Activating Token Index: 1014

Text #14

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.0802. Min Act: -0.1700

Data Index: 3889920 (Open Web Text)

Max Activating Token Index: 583

Text #15

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.0791. Min Act: -0.1700

Data Index: 2058629 (Open Web Text)

Max Activating Token Index: 453

Text #16

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.1054. Min Act: -0.1700

Data Index: 1270348 (Open Web Text)

Max Activating Token Index: 974

Text #17

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.1193. Min Act: -0.1700

Data Index: 3103295 (Open Web Text)

Max Activating Token Index: 203

Text #18

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.0463. Min Act: -0.1700

Data Index: 2363505 (Open Web Text)

Max Activating Token Index: 747

Text #19

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.0511. Min Act: -0.1700

Data Index: 2273023 (Open Web Text)

Max Activating Token Index: 227