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

Dataset: Open Web Text

Neuron 2235 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: 4.1458. Min Range: -4.1458

Max Act: 4.1458. Min Act: -0.1700

Data Index: 113105 (Open Web Text)

Max Activating Token Index: 576

Text #1

Max Range: 4.1458. Min Range: -4.1458

Max Act: 4.0480. Min Act: -0.1700

Data Index: 974866 (Open Web Text)

Max Activating Token Index: 631

Text #2

Max Range: 4.1458. Min Range: -4.1458

Max Act: 4.0222. Min Act: -0.1700

Data Index: 5932896 (Open Web Text)

Max Activating Token Index: 231

Text #3

Max Range: 4.1458. Min Range: -4.1458

Max Act: 3.9435. Min Act: -0.1700

Data Index: 1194859 (Open Web Text)

Max Activating Token Index: 949

Text #4

Max Range: 4.1458. Min Range: -4.1458

Max Act: 3.9461. Min Act: -0.1700

Data Index: 3076484 (Open Web Text)

Max Activating Token Index: 182

Text #5

Max Range: 4.1458. Min Range: -4.1458

Max Act: 3.8356. Min Act: -0.1700

Data Index: 5055332 (Open Web Text)

Max Activating Token Index: 127

Text #6

Max Range: 4.1458. Min Range: -4.1458

Max Act: 3.8311. Min Act: -0.1700

Data Index: 6958175 (Open Web Text)

Max Activating Token Index: 742

Text #7

Max Range: 4.1458. Min Range: -4.1458

Max Act: 3.8179. Min Act: -0.1700

Data Index: 1769050 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 4.1458. Min Range: -4.1458

Max Act: 3.7736. Min Act: -0.1700

Data Index: 3412778 (Open Web Text)

Max Activating Token Index: 676

Text #9

Max Range: 4.1458. Min Range: -4.1458

Max Act: 3.8009. Min Act: -0.1700

Data Index: 4139585 (Open Web Text)

Max Activating Token Index: 701

Text #10

Max Range: 4.1458. Min Range: -4.1458

Max Act: 3.7623. Min Act: -0.1700

Data Index: 5090425 (Open Web Text)

Max Activating Token Index: 882

Text #11

Max Range: 4.1458. Min Range: -4.1458

Max Act: 3.7741. Min Act: -0.1700

Data Index: 8631904 (Open Web Text)

Max Activating Token Index: 599

Text #12

Max Range: 4.1458. Min Range: -4.1458

Max Act: 3.7749. Min Act: -0.1700

Data Index: 7612047 (Open Web Text)

Max Activating Token Index: 528

Text #13

Max Range: 4.1458. Min Range: -4.1458

Max Act: 3.7849. Min Act: -0.1700

Data Index: 3157867 (Open Web Text)

Max Activating Token Index: 593

Text #14

Max Range: 4.1458. Min Range: -4.1458

Max Act: 3.7305. Min Act: -0.1700

Data Index: 2543176 (Open Web Text)

Max Activating Token Index: 20

Text #15

Max Range: 4.1458. Min Range: -4.1458

Max Act: 3.7469. Min Act: -0.1700

Data Index: 6311152 (Open Web Text)

Max Activating Token Index: 227

Text #16

Max Range: 4.1458. Min Range: -4.1458

Max Act: 3.7204. Min Act: -0.1700

Data Index: 778099 (Open Web Text)

Max Activating Token Index: 252

Text #17

Max Range: 4.1458. Min Range: -4.1458

Max Act: 3.7176. Min Act: -0.1700

Data Index: 5611842 (Open Web Text)

Max Activating Token Index: 315

Text #18

Max Range: 4.1458. Min Range: -4.1458

Max Act: 3.7129. Min Act: -0.1700

Data Index: 4221658 (Open Web Text)

Max Activating Token Index: 365

Text #19

Max Range: 4.1458. Min Range: -4.1458

Max Act: 3.6970. Min Act: -0.1700

Data Index: 6107034 (Open Web Text)

Max Activating Token Index: 547