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

Dataset: Open Web Text

Neuron 207 in Layer 2

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: 3.1325. Min Range: -3.1325

Max Act: 3.1325. Min Act: -0.1700

Data Index: 4983200 (Open Web Text)

Max Activating Token Index: 454

Text #1

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9980. Min Act: -0.1700

Data Index: 7773943 (Open Web Text)

Max Activating Token Index: 988

Text #2

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0032. Min Act: -0.1700

Data Index: 759403 (Open Web Text)

Max Activating Token Index: 249

Text #3

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0012. Min Act: -0.1700

Data Index: 2318449 (Open Web Text)

Max Activating Token Index: 387

Text #4

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9985. Min Act: -0.1700

Data Index: 833691 (Open Web Text)

Max Activating Token Index: 982

Text #5

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9902. Min Act: -0.1700

Data Index: 1032603 (Open Web Text)

Max Activating Token Index: 35

Text #6

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9773. Min Act: -0.1700

Data Index: 7817537 (Open Web Text)

Max Activating Token Index: 553

Text #7

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9862. Min Act: -0.1700

Data Index: 323223 (Open Web Text)

Max Activating Token Index: 1009

Text #8

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9916. Min Act: -0.1700

Data Index: 6551020 (Open Web Text)

Max Activating Token Index: 384

Text #9

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9616. Min Act: -0.1700

Data Index: 2238475 (Open Web Text)

Max Activating Token Index: 652

Text #10

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9600. Min Act: -0.1700

Data Index: 4900387 (Open Web Text)

Max Activating Token Index: 432

Text #11

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9498. Min Act: -0.1700

Data Index: 5245430 (Open Web Text)

Max Activating Token Index: 939

Text #12

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9590. Min Act: -0.1700

Data Index: 6244661 (Open Web Text)

Max Activating Token Index: 767

Text #13

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9492. Min Act: -0.1700

Data Index: 421615 (Open Web Text)

Max Activating Token Index: 639

Text #14

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9565. Min Act: -0.1700

Data Index: 2737614 (Open Web Text)

Max Activating Token Index: 891

Text #15

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9402. Min Act: -0.1700

Data Index: 1181392 (Open Web Text)

Max Activating Token Index: 649

Text #16

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9552. Min Act: -0.1700

Data Index: 438754 (Open Web Text)

Max Activating Token Index: 653

Text #17

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9368. Min Act: -0.1700

Data Index: 8410973 (Open Web Text)

Max Activating Token Index: 515

Text #18

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9305. Min Act: -0.1700

Data Index: 2596885 (Open Web Text)

Max Activating Token Index: 567

Text #19

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9335. Min Act: -0.1700

Data Index: 4028911 (Open Web Text)

Max Activating Token Index: 330