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

Dataset: Open Web Text

Neuron 2473 in Layer 1

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: 3.0657. Min Range: -3.0657

Max Act: 3.0657. Min Act: -0.1700

Data Index: 7771514 (Open Web Text)

Max Activating Token Index: 695

Text #1

Max Range: 3.0657. Min Range: -3.0657

Max Act: 3.0237. Min Act: -0.1700

Data Index: 6478122 (Open Web Text)

Max Activating Token Index: 859

Text #2

Max Range: 3.0657. Min Range: -3.0657

Max Act: 2.9855. Min Act: -0.1700

Data Index: 1642361 (Open Web Text)

Max Activating Token Index: 389

Text #3

Max Range: 3.0657. Min Range: -3.0657

Max Act: 2.9925. Min Act: -0.1700

Data Index: 5941160 (Open Web Text)

Max Activating Token Index: 63

Text #4

Max Range: 3.0657. Min Range: -3.0657

Max Act: 2.9584. Min Act: -0.1700

Data Index: 1408997 (Open Web Text)

Max Activating Token Index: 401

Text #5

Max Range: 3.0657. Min Range: -3.0657

Max Act: 2.9611. Min Act: -0.1700

Data Index: 4172706 (Open Web Text)

Max Activating Token Index: 319

Text #6

Max Range: 3.0657. Min Range: -3.0657

Max Act: 2.9751. Min Act: -0.1700

Data Index: 5672732 (Open Web Text)

Max Activating Token Index: 526

Text #7

Max Range: 3.0657. Min Range: -3.0657

Max Act: 2.9469. Min Act: -0.1700

Data Index: 2965343 (Open Web Text)

Max Activating Token Index: 550

Text #8

Max Range: 3.0657. Min Range: -3.0657

Max Act: 2.9377. Min Act: -0.1700

Data Index: 6522293 (Open Web Text)

Max Activating Token Index: 734

Text #9

Max Range: 3.0657. Min Range: -3.0657

Max Act: 2.9240. Min Act: -0.1700

Data Index: 2148420 (Open Web Text)

Max Activating Token Index: 25

Text #10

Max Range: 3.0657. Min Range: -3.0657

Max Act: 2.9333. Min Act: -0.1700

Data Index: 1144873 (Open Web Text)

Max Activating Token Index: 538

Text #11

Max Range: 3.0657. Min Range: -3.0657

Max Act: 2.9371. Min Act: -0.1700

Data Index: 138118 (Open Web Text)

Max Activating Token Index: 750

Text #12

Max Range: 3.0657. Min Range: -3.0657

Max Act: 2.9165. Min Act: -0.1700

Data Index: 8744154 (Open Web Text)

Max Activating Token Index: 169

Text #13

Max Range: 3.0657. Min Range: -3.0657

Max Act: 2.9269. Min Act: -0.1700

Data Index: 7932876 (Open Web Text)

Max Activating Token Index: 518

Text #14

Max Range: 3.0657. Min Range: -3.0657

Max Act: 2.9253. Min Act: -0.1700

Data Index: 81484 (Open Web Text)

Max Activating Token Index: 283

Text #15

Max Range: 3.0657. Min Range: -3.0657

Max Act: 2.9297. Min Act: -0.1700

Data Index: 5445124 (Open Web Text)

Max Activating Token Index: 274

Text #16

Max Range: 3.0657. Min Range: -3.0657

Max Act: 2.9285. Min Act: -0.1700

Data Index: 5333509 (Open Web Text)

Max Activating Token Index: 382

Text #17

Max Range: 3.0657. Min Range: -3.0657

Max Act: 2.9600. Min Act: -0.1700

Data Index: 2191195 (Open Web Text)

Max Activating Token Index: 663

Text #18

Max Range: 3.0657. Min Range: -3.0657

Max Act: 2.9196. Min Act: -0.1700

Data Index: 810343 (Open Web Text)

Max Activating Token Index: 125

Text #19

Max Range: 3.0657. Min Range: -3.0657

Max Act: 2.8858. Min Act: -0.1700

Data Index: 6497001 (Open Web Text)

Max Activating Token Index: 932