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

Dataset: Open Web Text

Neuron 2013 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: 3.0635. Min Range: -3.0635

Max Act: 3.0635. Min Act: -0.1700

Data Index: 1168847 (Open Web Text)

Max Activating Token Index: 751

Text #1

Max Range: 3.0635. Min Range: -3.0635

Max Act: 3.0458. Min Act: -0.1700

Data Index: 1315833 (Open Web Text)

Max Activating Token Index: 104

Text #2

Max Range: 3.0635. Min Range: -3.0635

Max Act: 3.0280. Min Act: -0.1700

Data Index: 6178897 (Open Web Text)

Max Activating Token Index: 142

Text #3

Max Range: 3.0635. Min Range: -3.0635

Max Act: 3.0017. Min Act: -0.1700

Data Index: 949397 (Open Web Text)

Max Activating Token Index: 547

Text #4

Max Range: 3.0635. Min Range: -3.0635

Max Act: 2.9685. Min Act: -0.1700

Data Index: 1900075 (Open Web Text)

Max Activating Token Index: 34

Text #5

Max Range: 3.0635. Min Range: -3.0635

Max Act: 2.9522. Min Act: -0.1700

Data Index: 5882145 (Open Web Text)

Max Activating Token Index: 885

Text #6

Max Range: 3.0635. Min Range: -3.0635

Max Act: 2.9658. Min Act: -0.1700

Data Index: 1181145 (Open Web Text)

Max Activating Token Index: 309

Text #7

Max Range: 3.0635. Min Range: -3.0635

Max Act: 2.9353. Min Act: -0.1700

Data Index: 5596394 (Open Web Text)

Max Activating Token Index: 681

Text #8

Max Range: 3.0635. Min Range: -3.0635

Max Act: 2.9439. Min Act: -0.1700

Data Index: 10793 (Open Web Text)

Max Activating Token Index: 560

Text #9

Max Range: 3.0635. Min Range: -3.0635

Max Act: 2.9328. Min Act: -0.1700

Data Index: 8314133 (Open Web Text)

Max Activating Token Index: 426

Text #10

Max Range: 3.0635. Min Range: -3.0635

Max Act: 2.9408. Min Act: -0.1700

Data Index: 46904 (Open Web Text)

Max Activating Token Index: 39

Text #11

Max Range: 3.0635. Min Range: -3.0635

Max Act: 2.9305. Min Act: -0.1700

Data Index: 2026887 (Open Web Text)

Max Activating Token Index: 85

Text #12

Max Range: 3.0635. Min Range: -3.0635

Max Act: 2.9345. Min Act: -0.1700

Data Index: 1317724 (Open Web Text)

Max Activating Token Index: 484

Text #13

Max Range: 3.0635. Min Range: -3.0635

Max Act: 2.9270. Min Act: -0.1700

Data Index: 8205083 (Open Web Text)

Max Activating Token Index: 745

Text #14

Max Range: 3.0635. Min Range: -3.0635

Max Act: 2.9175. Min Act: -0.1700

Data Index: 2385967 (Open Web Text)

Max Activating Token Index: 36

Text #15

Max Range: 3.0635. Min Range: -3.0635

Max Act: 2.9262. Min Act: -0.1700

Data Index: 5663784 (Open Web Text)

Max Activating Token Index: 241

Text #16

Max Range: 3.0635. Min Range: -3.0635

Max Act: 2.9224. Min Act: -0.1700

Data Index: 7767445 (Open Web Text)

Max Activating Token Index: 429

Text #17

Max Range: 3.0635. Min Range: -3.0635

Max Act: 2.9340. Min Act: -0.1700

Data Index: 2707057 (Open Web Text)

Max Activating Token Index: 92

Text #18

Max Range: 3.0635. Min Range: -3.0635

Max Act: 2.9360. Min Act: -0.1700

Data Index: 5507204 (Open Web Text)

Max Activating Token Index: 924

Text #19

Max Range: 3.0635. Min Range: -3.0635

Max Act: 2.9199. Min Act: -0.1700

Data Index: 4899739 (Open Web Text)

Max Activating Token Index: 348