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

Dataset: Open Web Text

Neuron 2350 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: 3.5063. Min Range: -3.5063

Max Act: 3.5063. Min Act: -0.1700

Data Index: 3664579 (Open Web Text)

Max Activating Token Index: 230

Text #1

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.4071. Min Act: -0.1700

Data Index: 1109002 (Open Web Text)

Max Activating Token Index: 25

Text #2

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.3991. Min Act: -0.1700

Data Index: 6938157 (Open Web Text)

Max Activating Token Index: 32

Text #3

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.4021. Min Act: -0.1700

Data Index: 5869929 (Open Web Text)

Max Activating Token Index: 945

Text #4

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.4012. Min Act: -0.1700

Data Index: 5653003 (Open Web Text)

Max Activating Token Index: 617

Text #5

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.3785. Min Act: -0.1700

Data Index: 8315982 (Open Web Text)

Max Activating Token Index: 215

Text #6

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.3528. Min Act: -0.1700

Data Index: 7386471 (Open Web Text)

Max Activating Token Index: 58

Text #7

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.3365. Min Act: -0.1700

Data Index: 7426165 (Open Web Text)

Max Activating Token Index: 391

Text #8

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.3503. Min Act: -0.1700

Data Index: 6624357 (Open Web Text)

Max Activating Token Index: 289

Text #9

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.3404. Min Act: -0.1700

Data Index: 2784625 (Open Web Text)

Max Activating Token Index: 724

Text #10

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.3226. Min Act: -0.1700

Data Index: 467979 (Open Web Text)

Max Activating Token Index: 557

Text #11

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.3555. Min Act: -0.1700

Data Index: 485851 (Open Web Text)

Max Activating Token Index: 367

Text #12

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.3362. Min Act: -0.1700

Data Index: 4761952 (Open Web Text)

Max Activating Token Index: 577

Text #13

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.3263. Min Act: -0.1700

Data Index: 8710735 (Open Web Text)

Max Activating Token Index: 543

Text #14

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.3262. Min Act: -0.1700

Data Index: 6212805 (Open Web Text)

Max Activating Token Index: 193

Text #15

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.3442. Min Act: -0.1700

Data Index: 8310680 (Open Web Text)

Max Activating Token Index: 498

Text #16

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.3380. Min Act: -0.1700

Data Index: 6212806 (Open Web Text)

Max Activating Token Index: 113

Text #17

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.3307. Min Act: -0.1700

Data Index: 6000263 (Open Web Text)

Max Activating Token Index: 651

Text #18

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.3250. Min Act: -0.1700

Data Index: 2857677 (Open Web Text)

Max Activating Token Index: 35

Text #19

Max Range: 3.5063. Min Range: -3.5063

Max Act: 3.3083. Min Act: -0.1700

Data Index: 4703957 (Open Web Text)

Max Activating Token Index: 1019