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

Dataset: Open Web Text

Neuron 2596 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: 3.9607. Min Range: -3.9607

Max Act: 3.9607. Min Act: -0.1700

Data Index: 3871687 (Open Web Text)

Max Activating Token Index: 943

Text #1

Max Range: 3.9607. Min Range: -3.9607

Max Act: 3.9200. Min Act: -0.1700

Data Index: 2798816 (Open Web Text)

Max Activating Token Index: 460

Text #2

Max Range: 3.9607. Min Range: -3.9607

Max Act: 3.9199. Min Act: -0.1700

Data Index: 349557 (Open Web Text)

Max Activating Token Index: 785

Text #3

Max Range: 3.9607. Min Range: -3.9607

Max Act: 3.9310. Min Act: -0.1700

Data Index: 2855712 (Open Web Text)

Max Activating Token Index: 477

Text #4

Max Range: 3.9607. Min Range: -3.9607

Max Act: 3.8755. Min Act: -0.1700

Data Index: 8378933 (Open Web Text)

Max Activating Token Index: 602

Text #5

Max Range: 3.9607. Min Range: -3.9607

Max Act: 3.8707. Min Act: -0.1700

Data Index: 2094754 (Open Web Text)

Max Activating Token Index: 282

Text #6

Max Range: 3.9607. Min Range: -3.9607

Max Act: 3.8769. Min Act: -0.1700

Data Index: 6654928 (Open Web Text)

Max Activating Token Index: 590

Text #7

Max Range: 3.9607. Min Range: -3.9607

Max Act: 3.8832. Min Act: -0.1700

Data Index: 2810082 (Open Web Text)

Max Activating Token Index: 272

Text #8

Max Range: 3.9607. Min Range: -3.9607

Max Act: 3.8613. Min Act: -0.1700

Data Index: 4747545 (Open Web Text)

Max Activating Token Index: 444

Text #9

Max Range: 3.9607. Min Range: -3.9607

Max Act: 3.8739. Min Act: -0.1700

Data Index: 7384147 (Open Web Text)

Max Activating Token Index: 593

Text #10

Max Range: 3.9607. Min Range: -3.9607

Max Act: 3.8658. Min Act: -0.1700

Data Index: 7762921 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 3.9607. Min Range: -3.9607

Max Act: 3.8251. Min Act: -0.1700

Data Index: 8084512 (Open Web Text)

Max Activating Token Index: 291

Text #12

Max Range: 3.9607. Min Range: -3.9607

Max Act: 3.8633. Min Act: -0.1700

Data Index: 3271515 (Open Web Text)

Max Activating Token Index: 806

Text #13

Max Range: 3.9607. Min Range: -3.9607

Max Act: 3.8502. Min Act: -0.1700

Data Index: 6277430 (Open Web Text)

Max Activating Token Index: 96

Text #14

Max Range: 3.9607. Min Range: -3.9607

Max Act: 3.8609. Min Act: -0.1700

Data Index: 2064592 (Open Web Text)

Max Activating Token Index: 752

Text #15

Max Range: 3.9607. Min Range: -3.9607

Max Act: 3.8351. Min Act: -0.1700

Data Index: 3639327 (Open Web Text)

Max Activating Token Index: 558

Text #16

Max Range: 3.9607. Min Range: -3.9607

Max Act: 3.8403. Min Act: -0.1700

Data Index: 5749249 (Open Web Text)

Max Activating Token Index: 870

Text #17

Max Range: 3.9607. Min Range: -3.9607

Max Act: 3.8243. Min Act: -0.1700

Data Index: 1387523 (Open Web Text)

Max Activating Token Index: 477

Text #18

Max Range: 3.9607. Min Range: -3.9607

Max Act: 3.8273. Min Act: -0.1700

Data Index: 6819484 (Open Web Text)

Max Activating Token Index: 590

Text #19

Max Range: 3.9607. Min Range: -3.9607

Max Act: 3.8206. Min Act: -0.1700

Data Index: 7014695 (Open Web Text)

Max Activating Token Index: 974