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

Dataset: Open Web Text

Neuron 1126 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: 3.3732. Min Range: -3.3732

Max Act: 3.3732. Min Act: -0.1700

Data Index: 4258260 (Open Web Text)

Max Activating Token Index: 890

Text #1

Max Range: 3.3732. Min Range: -3.3732

Max Act: 3.3381. Min Act: -0.1700

Data Index: 6782759 (Open Web Text)

Max Activating Token Index: 96

Text #2

Max Range: 3.3732. Min Range: -3.3732

Max Act: 3.3357. Min Act: -0.1700

Data Index: 6268156 (Open Web Text)

Max Activating Token Index: 931

Text #3

Max Range: 3.3732. Min Range: -3.3732

Max Act: 3.3339. Min Act: -0.1700

Data Index: 5886096 (Open Web Text)

Max Activating Token Index: 812

Text #4

Max Range: 3.3732. Min Range: -3.3732

Max Act: 3.3431. Min Act: -0.1700

Data Index: 7389287 (Open Web Text)

Max Activating Token Index: 154

Text #5

Max Range: 3.3732. Min Range: -3.3732

Max Act: 3.2494. Min Act: -0.1700

Data Index: 5984778 (Open Web Text)

Max Activating Token Index: 873

Text #6

Max Range: 3.3732. Min Range: -3.3732

Max Act: 3.2306. Min Act: -0.1700

Data Index: 371414 (Open Web Text)

Max Activating Token Index: 751

Text #7

Max Range: 3.3732. Min Range: -3.3732

Max Act: 3.2337. Min Act: -0.1700

Data Index: 3791706 (Open Web Text)

Max Activating Token Index: 821

Text #8

Max Range: 3.3732. Min Range: -3.3732

Max Act: 3.2243. Min Act: -0.1700

Data Index: 6017023 (Open Web Text)

Max Activating Token Index: 510

Text #9

Max Range: 3.3732. Min Range: -3.3732

Max Act: 3.2389. Min Act: -0.1700

Data Index: 6517295 (Open Web Text)

Max Activating Token Index: 778

Text #10

Max Range: 3.3732. Min Range: -3.3732

Max Act: 3.2180. Min Act: -0.1700

Data Index: 5311801 (Open Web Text)

Max Activating Token Index: 313

Text #11

Max Range: 3.3732. Min Range: -3.3732

Max Act: 3.1847. Min Act: -0.1700

Data Index: 7475992 (Open Web Text)

Max Activating Token Index: 551

Text #12

Max Range: 3.3732. Min Range: -3.3732

Max Act: 3.1892. Min Act: -0.1700

Data Index: 7804975 (Open Web Text)

Max Activating Token Index: 474

Text #13

Max Range: 3.3732. Min Range: -3.3732

Max Act: 3.1963. Min Act: -0.1700

Data Index: 8321843 (Open Web Text)

Max Activating Token Index: 1011

Text #14

Max Range: 3.3732. Min Range: -3.3732

Max Act: 3.1726. Min Act: -0.1700

Data Index: 6482615 (Open Web Text)

Max Activating Token Index: 343

Text #15

Max Range: 3.3732. Min Range: -3.3732

Max Act: 3.2028. Min Act: -0.1700

Data Index: 4257012 (Open Web Text)

Max Activating Token Index: 536

Text #16

Max Range: 3.3732. Min Range: -3.3732

Max Act: 3.1756. Min Act: -0.1700

Data Index: 2310999 (Open Web Text)

Max Activating Token Index: 520

Text #17

Max Range: 3.3732. Min Range: -3.3732

Max Act: 3.1773. Min Act: -0.1700

Data Index: 1347506 (Open Web Text)

Max Activating Token Index: 876

Text #18

Max Range: 3.3732. Min Range: -3.3732

Max Act: 3.1671. Min Act: -0.1700

Data Index: 5113194 (Open Web Text)

Max Activating Token Index: 314

Text #19

Max Range: 3.3732. Min Range: -3.3732

Max Act: 3.1641. Min Act: -0.1700

Data Index: 2085346 (Open Web Text)

Max Activating Token Index: 914